weights: add darwin-28r base model (full safetensors + tokenizer + config)
Browse files- .gitattributes +1 -0
- darwin-28r/.eval_results/gpqa_diamond.yaml +9 -0
- darwin-28r/README.md +241 -0
- darwin-28r/chat_template.jinja +88 -0
- darwin-28r/config.json +147 -0
- darwin-28r/generation_config.json +13 -0
- darwin-28r/model-00001-of-00012.safetensors +3 -0
- darwin-28r/model-00002-of-00012.safetensors +3 -0
- darwin-28r/model-00003-of-00012.safetensors +3 -0
- darwin-28r/model-00004-of-00012.safetensors +3 -0
- darwin-28r/model-00005-of-00012.safetensors +3 -0
- darwin-28r/model-00006-of-00012.safetensors +3 -0
- darwin-28r/model-00007-of-00012.safetensors +3 -0
- darwin-28r/model-00008-of-00012.safetensors +3 -0
- darwin-28r/model-00009-of-00012.safetensors +3 -0
- darwin-28r/model-00010-of-00012.safetensors +3 -0
- darwin-28r/model-00011-of-00012.safetensors +3 -0
- darwin-28r/model-00012-of-00012.safetensors +3 -0
- darwin-28r/model.safetensors.index.json +859 -0
- darwin-28r/tokenizer.json +3 -0
- darwin-28r/tokenizer_config.json +300 -0
- darwin-28r/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
다운로드.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
image.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
다운로드.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
image.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
darwin-28r/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
darwin-28r/.eval_results/gpqa_diamond.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: Idavidrein/gpqa
|
| 3 |
+
task_id: diamond
|
| 4 |
+
value: 89.39
|
| 5 |
+
date: "2026-05-17"
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/FINAL-Bench/Darwin-28B-REASON
|
| 8 |
+
name: Darwin-28B-REASON Benchmark (Darwin-DELPHI)
|
| 9 |
+
user: vidraft
|
darwin-28r/README.md
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
- ko
|
| 7 |
+
- ja
|
| 8 |
+
- multilingual
|
| 9 |
+
library_name: transformers
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
+
tags:
|
| 12 |
+
- darwin
|
| 13 |
+
- darwin-reason
|
| 14 |
+
- reasoning
|
| 15 |
+
- advanced-reasoning
|
| 16 |
+
- chain-of-thought
|
| 17 |
+
- thinking
|
| 18 |
+
- reasoning-trace-distillation
|
| 19 |
+
- rtd
|
| 20 |
+
- darwin-delphi
|
| 21 |
+
- test-time-compute
|
| 22 |
+
- qwen3.6
|
| 23 |
+
- qwen
|
| 24 |
+
- gpqa
|
| 25 |
+
- benchmark
|
| 26 |
+
- open-source
|
| 27 |
+
- apache-2.0
|
| 28 |
+
- proto-agi
|
| 29 |
+
- vidraft
|
| 30 |
+
- eval-results
|
| 31 |
+
base_model:
|
| 32 |
+
- FINAL-Bench/Darwin-28B-Opus
|
| 33 |
+
base_model_relation: finetune
|
| 34 |
+
model-index:
|
| 35 |
+
- name: Darwin-28B-REASON
|
| 36 |
+
results:
|
| 37 |
+
- task:
|
| 38 |
+
type: text-generation
|
| 39 |
+
name: Graduate-Level Reasoning
|
| 40 |
+
dataset:
|
| 41 |
+
type: Idavidrein/gpqa
|
| 42 |
+
name: GPQA Diamond
|
| 43 |
+
config: gpqa_diamond
|
| 44 |
+
split: train
|
| 45 |
+
metrics:
|
| 46 |
+
- type: accuracy
|
| 47 |
+
value: 89.39
|
| 48 |
+
name: Accuracy (with Darwin-DELPHI)
|
| 49 |
+
verified: false
|
| 50 |
+
---
|
| 51 |
+
|
| 52 |
+
# Darwin-28B-REASON — Reasoning-Trace Distilled, Darwin-DELPHI Enhanced
|
| 53 |
+
|
| 54 |
+
<p align="center">
|
| 55 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-28B-REASON"><img src="https://img.shields.io/badge/⭐_GPQA_Diamond-89.39%25_Darwin--28B--REASON-gold?style=for-the-badge" alt="GPQA"></a>
|
| 56 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-28B-Opus"><img src="https://img.shields.io/badge/🧬_Base-Darwin--28B--Opus_(88.89%25)-blue?style=for-the-badge" alt="Opus"></a>
|
| 57 |
+
</p>
|
| 58 |
+
|
| 59 |
+
<p align="center">
|
| 60 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-36B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--36B--Opus_(88.4%25)-blue?style=for-the-badge" alt="36B"></a>
|
| 61 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-27B-Opus"><img src="https://img.shields.io/badge/🧬_Model-Darwin--27B--Opus_(86.9%25)-blue?style=for-the-badge" alt="27B"></a>
|
| 62 |
+
<a href="https://huggingface.co/FINAL-Bench/Darwin-9B-NEG"><img src="https://img.shields.io/badge/⚡_Model-Darwin--9B--NEG_(84.3%25)-purple?style=for-the-badge" alt="NEG"></a>
|
| 63 |
+
</p>
|
| 64 |
+
|
| 65 |
+
<p align="center">
|
| 66 |
+
<a href="https://huggingface.co/collections/FINAL-Bench/darwin-family"><img src="https://img.shields.io/badge/🏠_Darwin_Family-Collection-green?style=for-the-badge" alt="Family"></a>
|
| 67 |
+
<a href="https://huggingface.co/spaces/FINAL-Bench/Leaderboard"><img src="https://img.shields.io/badge/🏆_FINAL_Bench-Leaderboard-green?style=for-the-badge" alt="FINAL Bench"></a>
|
| 68 |
+
</p>
|
| 69 |
+
|
| 70 |
+
> Full standalone reasoning model derived from Darwin-28B-Opus · Reasoning-Trace Distillation (RTD) · Darwin-DELPHI test-time engine · 27.6 B · BF16 · Apache 2.0
|
| 71 |
+
> **GPQA Diamond: 89.39 % with Darwin-DELPHI**
|
| 72 |
+
|
| 73 |
+
---
|
| 74 |
+
|
| 75 |
+
## Overview
|
| 76 |
+
|
| 77 |
+
**Darwin-28B-REASON** is a reasoning-enhanced **standalone model** derived from **[Darwin-28B-Opus](https://huggingface.co/FINAL-Bench/Darwin-28B-Opus)**. It combines two components:
|
| 78 |
+
|
| 79 |
+
1. **Reasoning-Trace Distillation (RTD)** — a reasoning-trace distillation stage applied on top of the Darwin-28B-Opus base, producing this fully self-contained model (full weights, no external adapter required).
|
| 80 |
+
2. **Darwin-DELPHI** — a proprietary test-time reasoning engine.
|
| 81 |
+
|
| 82 |
+
Together they push graduate-level scientific reasoning to the top tier of the Darwin family: **89.39 %** on GPQA Diamond with Darwin-DELPHI. The model is released under **Apache-2.0**.
|
| 83 |
+
|
| 84 |
+
---
|
| 85 |
+
|
| 86 |
+
## 🧬 Darwin Platform & Research
|
| 87 |
+
|
| 88 |
+
**Darwin** is VIDRAFT's measuring-result-driven Korean reasoning model family — approximately **20 official models** plus **400+ community derivatives**, ranking **#3 globally on GPQA** among open models. The base model, **Darwin-28B-Opus**, is the HuggingFace-official **GPQA #3 (88.89 %)** model.
|
| 89 |
+
|
| 90 |
+
- **Platform technique** — MRI trust-weighted Evolutionary Merge ([arXiv:2605.14386](https://arxiv.org/abs/2605.14386)).
|
| 91 |
+
- **FINAL Bench** — VIDRAFT's evaluation framework (SSRN): MetaCognition **+14.05**, MA-ER Gap **0.392**.
|
| 92 |
+
- **4-layer Pre-AGI roadmap** — Darwin → AETHER → PROMETHEUS → HEPHAESTUS.
|
| 93 |
+
|
| 94 |
+
---
|
| 95 |
+
|
| 96 |
+
## 🧬 Model Lineage
|
| 97 |
+
|
| 98 |
+
| Role | Model | Contribution |
|
| 99 |
+
|:---:|:---|:---|
|
| 100 |
+
| **Base** | [`FINAL-Bench/Darwin-28B-Opus`](https://huggingface.co/FINAL-Bench/Darwin-28B-Opus) | GPQA #3 (88.89 %) Qwen3.6-generation reasoning backbone. |
|
| 101 |
+
| **RTD training** | reasoning-trace distillation | Distills complete reasoning chains into the model on top of the Opus base. |
|
| 102 |
+
| **Test-time engine** | Darwin-DELPHI | Proprietary inference-time consensus engine (not stored in weights). |
|
| 103 |
+
| **Result** | **`Darwin-28B-REASON`** (this model) | Full standalone RTD model + Darwin-DELPHI → **89.39 %** GPQA Diamond. |
|
| 104 |
+
|
| 105 |
+
---
|
| 106 |
+
|
| 107 |
+
## ⚙️ Technical Specifications
|
| 108 |
+
|
| 109 |
+
| Component | Value |
|
| 110 |
+
|:---|:---|
|
| 111 |
+
| Architecture | `Qwen3_5ForConditionalGeneration` (Qwen3.6 generation, hybrid linear + full attention; text path, `language_model_only`) |
|
| 112 |
+
| Parameters | **27.6 B** (BF16) — full standalone weights |
|
| 113 |
+
| Layers | 64 (3 linear : 1 full attention, `full_attention_interval = 4`) |
|
| 114 |
+
| Vocab size | 248 320 |
|
| 115 |
+
| Context length | 262 144 (long-chain reasoning supported) |
|
| 116 |
+
| Delivery | Full self-contained model — no external base or adapter required |
|
| 117 |
+
| Precision | bfloat16 |
|
| 118 |
+
| License | Apache 2.0 |
|
| 119 |
+
|
| 120 |
+
---
|
| 121 |
+
|
| 122 |
+
## 🔬 Core Techniques
|
| 123 |
+
|
| 124 |
+
### ① RTD — Reasoning-Trace Distillation
|
| 125 |
+
|
| 126 |
+
RTD distills **complete reasoning chains** from a publicly available mathematical corpus (Apache-2.0 source) on top of the Darwin-28B-Opus base, producing this standalone model. It strengthens long-form, multi-step scientific reasoning while preserving the base model's bilingual capability.
|
| 127 |
+
|
| 128 |
+
> The full RTD recipe (curation, trace selection, training schedule) is **proprietary** and is not disclosed.
|
| 129 |
+
|
| 130 |
+
### ② Darwin-DELPHI — Test-Time Reasoning Engine
|
| 131 |
+
|
| 132 |
+
**Darwin-DELPHI** is a proprietary test-time engine applied at inference. It performs **multi-sample cross-validation**, **re-examination of uncertain responses**, and **iterative self-critique**, converging to a **consensus** answer through a single-agent Delphi-method procedure.
|
| 133 |
+
|
| 134 |
+
> Darwin-DELPHI is **not stored in the model weights**. Its internal parameters — sampling counts, stage transitions, and decision thresholds — are a **trade secret** and are not published.
|
| 135 |
+
|
| 136 |
+
---
|
| 137 |
+
|
| 138 |
+
## 🏆 Benchmark — GPQA Diamond (198 questions)
|
| 139 |
+
|
| 140 |
+
GPQA Diamond is a 198-question, PhD-level graduate science reasoning benchmark.
|
| 141 |
+
|
| 142 |
+
| Model | Engine | **Accuracy** |
|
| 143 |
+
|:---|:---|:---:|
|
| 144 |
+
| Darwin-28B-Opus (base) | Standard | 88.89 % (176 / 198) |
|
| 145 |
+
| **Darwin-28B-REASON** | **Darwin-DELPHI** | **🥇 89.39 % (177 / 198)** |
|
| 146 |
+
|
| 147 |
+
The evaluation methodology for the Darwin-DELPHI result is **protected**; sample counts, staging, and thresholds are a **trade secret**.
|
| 148 |
+
|
| 149 |
+
---
|
| 150 |
+
|
| 151 |
+
## 🚀 Usage
|
| 152 |
+
|
| 153 |
+
Darwin-28B-REASON is a **full standalone model** — load it directly, no base model or adapter merge required.
|
| 154 |
+
|
| 155 |
+
```python
|
| 156 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 157 |
+
import torch
|
| 158 |
+
|
| 159 |
+
MODEL = "FINAL-Bench/Darwin-28B-REASON"
|
| 160 |
+
|
| 161 |
+
tok = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True)
|
| 162 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 163 |
+
MODEL,
|
| 164 |
+
torch_dtype=torch.bfloat16,
|
| 165 |
+
device_map="auto",
|
| 166 |
+
trust_remote_code=True,
|
| 167 |
+
)
|
| 168 |
+
model.eval()
|
| 169 |
+
|
| 170 |
+
messages = [
|
| 171 |
+
{"role": "user",
|
| 172 |
+
"content": "A particle moves along x(t) = t³ − 6t² + 9t. Find when it is at rest and classify the motion."}
|
| 173 |
+
]
|
| 174 |
+
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 175 |
+
inputs = tok(text, return_tensors="pt").to(model.device)
|
| 176 |
+
outputs = model.generate(**inputs, max_new_tokens=2048)
|
| 177 |
+
print(tok.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))
|
| 178 |
+
```
|
| 179 |
+
|
| 180 |
+
> The 89.39 % GPQA Diamond result is produced with the Darwin-DELPHI test-time engine applied on top of this model. Darwin-DELPHI is provided through the Darwin-series evaluation harness.
|
| 181 |
+
|
| 182 |
+
---
|
| 183 |
+
|
| 184 |
+
## 🎯 Recommended Use-Cases
|
| 185 |
+
|
| 186 |
+
- **Graduate-level STEM reasoning** (GPQA / science qualifying exams)
|
| 187 |
+
- **Mathematical problem solving** (MATH, AIME-style problems)
|
| 188 |
+
- **Complex multi-step chain-of-thought tasks**
|
| 189 |
+
- **Code generation and debugging**
|
| 190 |
+
- **Bilingual reasoning** (strong English + Korean; also Chinese / Japanese)
|
| 191 |
+
|
| 192 |
+
## ⚠️ Limitations
|
| 193 |
+
|
| 194 |
+
- The 27.6 B model in bfloat16 requires ≈ 55 GB of VRAM (a single A100-80GB or B200 is sufficient).
|
| 195 |
+
- The 89.39 % result depends on the Darwin-DELPHI test-time engine; the model on its own delivers strong but lower single-model accuracy.
|
| 196 |
+
- Optimised for English first, with secondary support for Korean, Chinese, and Japanese.
|
| 197 |
+
- Reasoning traces tend to be verbose — control with `max_new_tokens` as needed.
|
| 198 |
+
|
| 199 |
+
---
|
| 200 |
+
|
| 201 |
+
## 📚 Citation
|
| 202 |
+
|
| 203 |
+
```bibtex
|
| 204 |
+
@misc{darwin28b_reason_2026,
|
| 205 |
+
title = {Darwin-28B-REASON: Reasoning-Trace Distillation and Darwin-DELPHI Test-Time Reasoning on Darwin-28B-Opus},
|
| 206 |
+
author = {FINAL-Bench / Darwin Research Team},
|
| 207 |
+
year = {2026},
|
| 208 |
+
howpublished = {\url{https://huggingface.co/FINAL-Bench/Darwin-28B-REASON}},
|
| 209 |
+
note = {RTD + Darwin-DELPHI · 89.39 % GPQA Diamond}
|
| 210 |
+
}
|
| 211 |
+
|
| 212 |
+
@misc{darwin_family_2026,
|
| 213 |
+
title = {Darwin Family: MRI Trust-Weighted Evolutionary Merging for Reasoning Models},
|
| 214 |
+
author = {VIDRAFT / FINAL-Bench},
|
| 215 |
+
year = {2026},
|
| 216 |
+
howpublished = {\url{https://arxiv.org/abs/2605.14386}}
|
| 217 |
+
}
|
| 218 |
+
|
| 219 |
+
@misc{final_bench_2026,
|
| 220 |
+
title = {FINAL Bench: A Measuring-Result-Driven Evaluation Framework for Reasoning Models},
|
| 221 |
+
author = {VIDRAFT / FINAL-Bench},
|
| 222 |
+
year = {2026},
|
| 223 |
+
howpublished = {SSRN}
|
| 224 |
+
}
|
| 225 |
+
```
|
| 226 |
+
|
| 227 |
+
---
|
| 228 |
+
|
| 229 |
+
## 🔗 Related Darwin Models
|
| 230 |
+
|
| 231 |
+
- **Darwin-28B-Opus** — base model, Qwen3.6-27B × Opus distilled, GPQA 88.89 %
|
| 232 |
+
- **Darwin-36B-Opus** — MoE 36B, GPQA 88.4 %
|
| 233 |
+
- **Darwin-27B-Opus** — 27B dense (Qwen3.5 generation), GPQA 86.9 %
|
| 234 |
+
- **Darwin-9B-NEG** — 9B with Negentropy distillation, GPQA 84.3 %
|
| 235 |
+
- **Darwin-4B-Genesis** — smallest Darwin member
|
| 236 |
+
|
| 237 |
+
---
|
| 238 |
+
|
| 239 |
+
This model is introduced in [Darwin Family](https://arxiv.org/abs/2605.14386).
|
| 240 |
+
|
| 241 |
+
*Darwin-28B-REASON · RTD + Darwin-DELPHI · 89.39 % GPQA Diamond · FINAL-Bench*
|
darwin-28r/chat_template.jinja
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant
|
| 86 |
+
<think>
|
| 87 |
+
' }}
|
| 88 |
+
{%- endif %}
|
darwin-28r/config.json
ADDED
|
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"torch_dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248046,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"language_model_only": true,
|
| 10 |
+
"model_name": "FINAL-Bench/Darwin-28B-Opus",
|
| 11 |
+
"model_type": "qwen3_5",
|
| 12 |
+
"pad_token_id": 248055,
|
| 13 |
+
"text_config": {
|
| 14 |
+
"attention_bias": false,
|
| 15 |
+
"attention_dropout": 0.0,
|
| 16 |
+
"attn_output_gate": true,
|
| 17 |
+
"bos_token_id": 248044,
|
| 18 |
+
"torch_dtype": "bfloat16",
|
| 19 |
+
"eos_token_id": 248044,
|
| 20 |
+
"full_attention_interval": 4,
|
| 21 |
+
"head_dim": 256,
|
| 22 |
+
"hidden_act": "silu",
|
| 23 |
+
"hidden_size": 5120,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 17408,
|
| 26 |
+
"layer_types": [
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"linear_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"linear_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"linear_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"linear_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"linear_attention",
|
| 82 |
+
"full_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"linear_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"linear_attention",
|
| 90 |
+
"full_attention"
|
| 91 |
+
],
|
| 92 |
+
"linear_conv_kernel_dim": 4,
|
| 93 |
+
"linear_key_head_dim": 128,
|
| 94 |
+
"linear_num_key_heads": 16,
|
| 95 |
+
"linear_num_value_heads": 48,
|
| 96 |
+
"linear_value_head_dim": 128,
|
| 97 |
+
"mamba_ssm_dtype": "float32",
|
| 98 |
+
"max_position_embeddings": 262144,
|
| 99 |
+
"model_type": "qwen3_5_text",
|
| 100 |
+
"mtp_num_hidden_layers": 0,
|
| 101 |
+
"mtp_use_dedicated_embeddings": false,
|
| 102 |
+
"num_attention_heads": 24,
|
| 103 |
+
"num_hidden_layers": 64,
|
| 104 |
+
"num_key_value_heads": 4,
|
| 105 |
+
"output_gate_type": "swish",
|
| 106 |
+
"pad_token_id": null,
|
| 107 |
+
"partial_rotary_factor": 0.25,
|
| 108 |
+
"rms_norm_eps": 1e-06,
|
| 109 |
+
"rope_parameters": {
|
| 110 |
+
"mrope_interleaved": true,
|
| 111 |
+
"mrope_section": [
|
| 112 |
+
11,
|
| 113 |
+
11,
|
| 114 |
+
10
|
| 115 |
+
],
|
| 116 |
+
"partial_rotary_factor": 0.25,
|
| 117 |
+
"rope_theta": 10000000,
|
| 118 |
+
"rope_type": "default"
|
| 119 |
+
},
|
| 120 |
+
"tie_word_embeddings": false,
|
| 121 |
+
"use_cache": true,
|
| 122 |
+
"vocab_size": 248320
|
| 123 |
+
},
|
| 124 |
+
"tie_word_embeddings": false,
|
| 125 |
+
"unsloth_version": "2026.4.7",
|
| 126 |
+
"use_cache": false,
|
| 127 |
+
"video_token_id": 248057,
|
| 128 |
+
"vision_config": {
|
| 129 |
+
"deepstack_visual_indexes": [],
|
| 130 |
+
"depth": 27,
|
| 131 |
+
"torch_dtype": "bfloat16",
|
| 132 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 133 |
+
"hidden_size": 1152,
|
| 134 |
+
"in_channels": 3,
|
| 135 |
+
"initializer_range": 0.02,
|
| 136 |
+
"intermediate_size": 4304,
|
| 137 |
+
"model_type": "qwen3_5",
|
| 138 |
+
"num_heads": 16,
|
| 139 |
+
"num_position_embeddings": 2304,
|
| 140 |
+
"out_hidden_size": 5120,
|
| 141 |
+
"patch_size": 16,
|
| 142 |
+
"spatial_merge_size": 2,
|
| 143 |
+
"temporal_patch_size": 2
|
| 144 |
+
},
|
| 145 |
+
"vision_end_token_id": 248054,
|
| 146 |
+
"vision_start_token_id": 248053
|
| 147 |
+
}
|
darwin-28r/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.5.4"
|
| 13 |
+
}
|
darwin-28r/model-00001-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:994d372da0812952c05a3fb1093db5b1245e314385290892f0dce3883f4c2643
|
| 3 |
+
size 2542796928
|
darwin-28r/model-00002-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e64ae145bd2a05bbe117e9e7460f0923a662e5922154ada1951e1552f09dfc7e
|
| 3 |
+
size 4842451920
|
darwin-28r/model-00003-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fb3683af9ba0f0a594353b92281a38392609f2f1ad4b41cc3401d939f7ad0ba
|
| 3 |
+
size 4965227944
|
darwin-28r/model-00004-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebed374e90f05e0cc39d9027f234b7381b4bf354bb063016de4e29a6469080f0
|
| 3 |
+
size 4912819264
|
darwin-28r/model-00005-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60e45716ee9ab2b603cb585cd32a4b197d24736c5f2e2ae93ab1ca8c33c98a71
|
| 3 |
+
size 4986198544
|
darwin-28r/model-00006-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e467f105cc79892c78c1b779fc306f085b5b1ac7eacd81062352e6a4323bdf85
|
| 3 |
+
size 4912819320
|
darwin-28r/model-00007-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ace2d0452d1e9f2ef64e27facbd19da7b4307d9cd5ebf9b6c4d4600cbfecff7
|
| 3 |
+
size 4932703272
|
darwin-28r/model-00008-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cff78de6d601b80f5dc04ddd8ea4877ec561e7cbaee4f353ba154b94d461087e
|
| 3 |
+
size 4966314576
|
darwin-28r/model-00009-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4253dadea3ef63d3c3f51bfc87f2034151e886671c62ce1e3d69d510c437d3a
|
| 3 |
+
size 4964162248
|
darwin-28r/model-00010-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f83b44f9ade06b666ae2f33730c47537448210a90937529cb19f5d833ff7d74
|
| 3 |
+
size 4933789824
|
darwin-28r/model-00011-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c87926a196baf90b69e9f6d1971d477b40c10a2cb62b5e219d54f80742f16d0c
|
| 3 |
+
size 4965228032
|
darwin-28r/model-00012-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48cf9df23c1045de13d59086a55452a78c230f862e53edfb2adc3edf6e01b6d7
|
| 3 |
+
size 1867596944
|
darwin-28r/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 26895998464,
|
| 4 |
+
"total_size": 53791996928
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00012.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00002-of-00012.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00012.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00012.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00012.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00012.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00012.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00002-of-00012.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00002-of-00012.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00012.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00002-of-00012.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
| 22 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 23 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00012.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00012.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00012.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00012.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00012.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00012.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00012.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00012.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00012.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
| 35 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
| 36 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 37 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 49 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 50 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 51 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 54 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 55 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
| 61 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
| 62 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 71 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 74 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 75 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 76 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 85 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 88 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 89 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 90 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 99 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 102 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 103 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 104 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 107 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 108 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
| 114 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
| 115 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 124 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 127 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 128 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 129 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 138 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 141 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 142 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 143 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 152 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 155 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 156 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 157 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 160 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 161 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00012.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00012.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
| 167 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
| 168 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00012.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00012.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00012.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00012.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00012.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00012.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00012.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00012.safetensors",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00012.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
| 180 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
| 181 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 182 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 191 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 194 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 195 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 196 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 205 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 208 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 209 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 210 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 219 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 222 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 223 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 224 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 227 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 228 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
| 234 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
| 235 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 244 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 247 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 248 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 249 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 261 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 262 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 263 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 272 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 275 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 276 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 277 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 280 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 281 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
| 287 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
| 288 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 297 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 300 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 301 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 302 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 311 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 314 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 315 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 316 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 319 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 320 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
| 326 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
| 327 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 336 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 339 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 340 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 341 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 344 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 345 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00012.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00012.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
| 351 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
| 352 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 353 |
+
"model.language_model.layers.32.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 354 |
+
"model.language_model.layers.32.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 355 |
+
"model.language_model.layers.32.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 356 |
+
"model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 357 |
+
"model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 358 |
+
"model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 359 |
+
"model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 360 |
+
"model.language_model.layers.32.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 361 |
+
"model.language_model.layers.32.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 362 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 363 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 364 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 365 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 366 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 367 |
+
"model.language_model.layers.33.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 368 |
+
"model.language_model.layers.33.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 369 |
+
"model.language_model.layers.33.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 370 |
+
"model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 371 |
+
"model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 372 |
+
"model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 373 |
+
"model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 374 |
+
"model.language_model.layers.33.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 375 |
+
"model.language_model.layers.33.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 376 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 377 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 378 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 379 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 380 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 381 |
+
"model.language_model.layers.34.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 382 |
+
"model.language_model.layers.34.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 383 |
+
"model.language_model.layers.34.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 384 |
+
"model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 385 |
+
"model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 386 |
+
"model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 387 |
+
"model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 388 |
+
"model.language_model.layers.34.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 389 |
+
"model.language_model.layers.34.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 390 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 391 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 392 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 393 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 394 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 395 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 396 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 397 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 398 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 399 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
|
| 400 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
| 401 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
| 402 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
|
| 403 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
| 404 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
| 405 |
+
"model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 406 |
+
"model.language_model.layers.36.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 407 |
+
"model.language_model.layers.36.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 408 |
+
"model.language_model.layers.36.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 409 |
+
"model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 410 |
+
"model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 411 |
+
"model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 412 |
+
"model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 413 |
+
"model.language_model.layers.36.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 414 |
+
"model.language_model.layers.36.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 415 |
+
"model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 416 |
+
"model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 417 |
+
"model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 418 |
+
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 419 |
+
"model.language_model.layers.37.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 420 |
+
"model.language_model.layers.37.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 421 |
+
"model.language_model.layers.37.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 422 |
+
"model.language_model.layers.37.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 423 |
+
"model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 424 |
+
"model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 425 |
+
"model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 426 |
+
"model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 427 |
+
"model.language_model.layers.37.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 428 |
+
"model.language_model.layers.37.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 429 |
+
"model.language_model.layers.37.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 430 |
+
"model.language_model.layers.37.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 431 |
+
"model.language_model.layers.37.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 432 |
+
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 433 |
+
"model.language_model.layers.38.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 434 |
+
"model.language_model.layers.38.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 435 |
+
"model.language_model.layers.38.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 436 |
+
"model.language_model.layers.38.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 437 |
+
"model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 438 |
+
"model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 439 |
+
"model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 440 |
+
"model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 441 |
+
"model.language_model.layers.38.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 442 |
+
"model.language_model.layers.38.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 443 |
+
"model.language_model.layers.38.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 444 |
+
"model.language_model.layers.38.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 445 |
+
"model.language_model.layers.38.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 446 |
+
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 447 |
+
"model.language_model.layers.39.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 448 |
+
"model.language_model.layers.39.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 449 |
+
"model.language_model.layers.39.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 450 |
+
"model.language_model.layers.39.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 451 |
+
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 452 |
+
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
|
| 453 |
+
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
| 454 |
+
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
| 455 |
+
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
|
| 456 |
+
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
| 457 |
+
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
| 458 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 459 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 460 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 461 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 462 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 463 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 464 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 465 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 466 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 467 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 468 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 469 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 470 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 471 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 472 |
+
"model.language_model.layers.40.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 473 |
+
"model.language_model.layers.40.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 474 |
+
"model.language_model.layers.40.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 475 |
+
"model.language_model.layers.40.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 476 |
+
"model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 477 |
+
"model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 478 |
+
"model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 479 |
+
"model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 480 |
+
"model.language_model.layers.40.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 481 |
+
"model.language_model.layers.40.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 482 |
+
"model.language_model.layers.40.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 483 |
+
"model.language_model.layers.40.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 484 |
+
"model.language_model.layers.40.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 485 |
+
"model.language_model.layers.40.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 486 |
+
"model.language_model.layers.41.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 487 |
+
"model.language_model.layers.41.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 488 |
+
"model.language_model.layers.41.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 489 |
+
"model.language_model.layers.41.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 490 |
+
"model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 491 |
+
"model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 492 |
+
"model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 493 |
+
"model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 494 |
+
"model.language_model.layers.41.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 495 |
+
"model.language_model.layers.41.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 496 |
+
"model.language_model.layers.41.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 497 |
+
"model.language_model.layers.41.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 498 |
+
"model.language_model.layers.41.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 499 |
+
"model.language_model.layers.41.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 500 |
+
"model.language_model.layers.42.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 501 |
+
"model.language_model.layers.42.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 502 |
+
"model.language_model.layers.42.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 503 |
+
"model.language_model.layers.42.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 504 |
+
"model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 505 |
+
"model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 506 |
+
"model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 507 |
+
"model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 508 |
+
"model.language_model.layers.42.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 509 |
+
"model.language_model.layers.42.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 510 |
+
"model.language_model.layers.42.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 511 |
+
"model.language_model.layers.42.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 512 |
+
"model.language_model.layers.42.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 513 |
+
"model.language_model.layers.42.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 514 |
+
"model.language_model.layers.43.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 515 |
+
"model.language_model.layers.43.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 516 |
+
"model.language_model.layers.43.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 517 |
+
"model.language_model.layers.43.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 518 |
+
"model.language_model.layers.43.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 519 |
+
"model.language_model.layers.43.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
|
| 520 |
+
"model.language_model.layers.43.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
| 521 |
+
"model.language_model.layers.43.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
| 522 |
+
"model.language_model.layers.43.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
|
| 523 |
+
"model.language_model.layers.43.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
| 524 |
+
"model.language_model.layers.43.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
| 525 |
+
"model.language_model.layers.44.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 526 |
+
"model.language_model.layers.44.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 527 |
+
"model.language_model.layers.44.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 528 |
+
"model.language_model.layers.44.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 529 |
+
"model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 530 |
+
"model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 531 |
+
"model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 532 |
+
"model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 533 |
+
"model.language_model.layers.44.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 534 |
+
"model.language_model.layers.44.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 535 |
+
"model.language_model.layers.44.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 536 |
+
"model.language_model.layers.44.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 537 |
+
"model.language_model.layers.44.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 538 |
+
"model.language_model.layers.44.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 539 |
+
"model.language_model.layers.45.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 540 |
+
"model.language_model.layers.45.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 541 |
+
"model.language_model.layers.45.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 542 |
+
"model.language_model.layers.45.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 543 |
+
"model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 544 |
+
"model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 545 |
+
"model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 546 |
+
"model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 547 |
+
"model.language_model.layers.45.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 548 |
+
"model.language_model.layers.45.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 549 |
+
"model.language_model.layers.45.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 550 |
+
"model.language_model.layers.45.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 551 |
+
"model.language_model.layers.45.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 552 |
+
"model.language_model.layers.45.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 553 |
+
"model.language_model.layers.46.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 554 |
+
"model.language_model.layers.46.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 555 |
+
"model.language_model.layers.46.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 556 |
+
"model.language_model.layers.46.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 557 |
+
"model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 558 |
+
"model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 559 |
+
"model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 560 |
+
"model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 561 |
+
"model.language_model.layers.46.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 562 |
+
"model.language_model.layers.46.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 563 |
+
"model.language_model.layers.46.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 564 |
+
"model.language_model.layers.46.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 565 |
+
"model.language_model.layers.46.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 566 |
+
"model.language_model.layers.46.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 567 |
+
"model.language_model.layers.47.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 568 |
+
"model.language_model.layers.47.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 569 |
+
"model.language_model.layers.47.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 570 |
+
"model.language_model.layers.47.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 571 |
+
"model.language_model.layers.47.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 572 |
+
"model.language_model.layers.47.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
|
| 573 |
+
"model.language_model.layers.47.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
| 574 |
+
"model.language_model.layers.47.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
| 575 |
+
"model.language_model.layers.47.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
|
| 576 |
+
"model.language_model.layers.47.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
| 577 |
+
"model.language_model.layers.47.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
| 578 |
+
"model.language_model.layers.48.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 579 |
+
"model.language_model.layers.48.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 580 |
+
"model.language_model.layers.48.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 581 |
+
"model.language_model.layers.48.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 582 |
+
"model.language_model.layers.48.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 583 |
+
"model.language_model.layers.48.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 584 |
+
"model.language_model.layers.48.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 585 |
+
"model.language_model.layers.48.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 586 |
+
"model.language_model.layers.48.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 587 |
+
"model.language_model.layers.48.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 588 |
+
"model.language_model.layers.48.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 589 |
+
"model.language_model.layers.48.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 590 |
+
"model.language_model.layers.48.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 591 |
+
"model.language_model.layers.48.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 592 |
+
"model.language_model.layers.49.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 593 |
+
"model.language_model.layers.49.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 594 |
+
"model.language_model.layers.49.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 595 |
+
"model.language_model.layers.49.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 596 |
+
"model.language_model.layers.49.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 597 |
+
"model.language_model.layers.49.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 598 |
+
"model.language_model.layers.49.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 599 |
+
"model.language_model.layers.49.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 600 |
+
"model.language_model.layers.49.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 601 |
+
"model.language_model.layers.49.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 602 |
+
"model.language_model.layers.49.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 603 |
+
"model.language_model.layers.49.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 604 |
+
"model.language_model.layers.49.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 605 |
+
"model.language_model.layers.49.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 606 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 607 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 608 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 609 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 610 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 611 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 612 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 613 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 614 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 615 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 616 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 617 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 618 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 619 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 620 |
+
"model.language_model.layers.50.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 621 |
+
"model.language_model.layers.50.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 622 |
+
"model.language_model.layers.50.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 623 |
+
"model.language_model.layers.50.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 624 |
+
"model.language_model.layers.50.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 625 |
+
"model.language_model.layers.50.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 626 |
+
"model.language_model.layers.50.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 627 |
+
"model.language_model.layers.50.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 628 |
+
"model.language_model.layers.50.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 629 |
+
"model.language_model.layers.50.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 630 |
+
"model.language_model.layers.50.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 631 |
+
"model.language_model.layers.50.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 632 |
+
"model.language_model.layers.50.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 633 |
+
"model.language_model.layers.50.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 634 |
+
"model.language_model.layers.51.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 635 |
+
"model.language_model.layers.51.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 636 |
+
"model.language_model.layers.51.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 637 |
+
"model.language_model.layers.51.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 638 |
+
"model.language_model.layers.51.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 639 |
+
"model.language_model.layers.51.self_attn.k_norm.weight": "model-00010-of-00012.safetensors",
|
| 640 |
+
"model.language_model.layers.51.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
| 641 |
+
"model.language_model.layers.51.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
| 642 |
+
"model.language_model.layers.51.self_attn.q_norm.weight": "model-00010-of-00012.safetensors",
|
| 643 |
+
"model.language_model.layers.51.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
| 644 |
+
"model.language_model.layers.51.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
| 645 |
+
"model.language_model.layers.52.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 646 |
+
"model.language_model.layers.52.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 647 |
+
"model.language_model.layers.52.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 648 |
+
"model.language_model.layers.52.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 649 |
+
"model.language_model.layers.52.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 650 |
+
"model.language_model.layers.52.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 651 |
+
"model.language_model.layers.52.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 652 |
+
"model.language_model.layers.52.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 653 |
+
"model.language_model.layers.52.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 654 |
+
"model.language_model.layers.52.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 655 |
+
"model.language_model.layers.52.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 656 |
+
"model.language_model.layers.52.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 657 |
+
"model.language_model.layers.52.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 658 |
+
"model.language_model.layers.52.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 659 |
+
"model.language_model.layers.53.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 660 |
+
"model.language_model.layers.53.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 661 |
+
"model.language_model.layers.53.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 662 |
+
"model.language_model.layers.53.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 663 |
+
"model.language_model.layers.53.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 664 |
+
"model.language_model.layers.53.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 665 |
+
"model.language_model.layers.53.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 666 |
+
"model.language_model.layers.53.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 667 |
+
"model.language_model.layers.53.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 668 |
+
"model.language_model.layers.53.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 669 |
+
"model.language_model.layers.53.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 670 |
+
"model.language_model.layers.53.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 671 |
+
"model.language_model.layers.53.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 672 |
+
"model.language_model.layers.53.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 673 |
+
"model.language_model.layers.54.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 674 |
+
"model.language_model.layers.54.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 675 |
+
"model.language_model.layers.54.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 676 |
+
"model.language_model.layers.54.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 677 |
+
"model.language_model.layers.54.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 678 |
+
"model.language_model.layers.54.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 679 |
+
"model.language_model.layers.54.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 680 |
+
"model.language_model.layers.54.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 681 |
+
"model.language_model.layers.54.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 682 |
+
"model.language_model.layers.54.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 683 |
+
"model.language_model.layers.54.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 684 |
+
"model.language_model.layers.54.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 685 |
+
"model.language_model.layers.54.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 686 |
+
"model.language_model.layers.54.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 687 |
+
"model.language_model.layers.55.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 688 |
+
"model.language_model.layers.55.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 689 |
+
"model.language_model.layers.55.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 690 |
+
"model.language_model.layers.55.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 691 |
+
"model.language_model.layers.55.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 692 |
+
"model.language_model.layers.55.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
|
| 693 |
+
"model.language_model.layers.55.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
| 694 |
+
"model.language_model.layers.55.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
| 695 |
+
"model.language_model.layers.55.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
|
| 696 |
+
"model.language_model.layers.55.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
| 697 |
+
"model.language_model.layers.55.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
| 698 |
+
"model.language_model.layers.56.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 699 |
+
"model.language_model.layers.56.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 700 |
+
"model.language_model.layers.56.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 701 |
+
"model.language_model.layers.56.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 702 |
+
"model.language_model.layers.56.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 703 |
+
"model.language_model.layers.56.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 704 |
+
"model.language_model.layers.56.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 705 |
+
"model.language_model.layers.56.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 706 |
+
"model.language_model.layers.56.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 707 |
+
"model.language_model.layers.56.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 708 |
+
"model.language_model.layers.56.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 709 |
+
"model.language_model.layers.56.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 710 |
+
"model.language_model.layers.56.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 711 |
+
"model.language_model.layers.56.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 712 |
+
"model.language_model.layers.57.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 713 |
+
"model.language_model.layers.57.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 714 |
+
"model.language_model.layers.57.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 715 |
+
"model.language_model.layers.57.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 716 |
+
"model.language_model.layers.57.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 717 |
+
"model.language_model.layers.57.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 718 |
+
"model.language_model.layers.57.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 719 |
+
"model.language_model.layers.57.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 720 |
+
"model.language_model.layers.57.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 721 |
+
"model.language_model.layers.57.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 722 |
+
"model.language_model.layers.57.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 723 |
+
"model.language_model.layers.57.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 724 |
+
"model.language_model.layers.57.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 725 |
+
"model.language_model.layers.57.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 726 |
+
"model.language_model.layers.58.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 727 |
+
"model.language_model.layers.58.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 728 |
+
"model.language_model.layers.58.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 729 |
+
"model.language_model.layers.58.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 730 |
+
"model.language_model.layers.58.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 731 |
+
"model.language_model.layers.58.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 732 |
+
"model.language_model.layers.58.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 733 |
+
"model.language_model.layers.58.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 734 |
+
"model.language_model.layers.58.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 735 |
+
"model.language_model.layers.58.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 736 |
+
"model.language_model.layers.58.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 737 |
+
"model.language_model.layers.58.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 738 |
+
"model.language_model.layers.58.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 739 |
+
"model.language_model.layers.58.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 740 |
+
"model.language_model.layers.59.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 741 |
+
"model.language_model.layers.59.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 742 |
+
"model.language_model.layers.59.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 743 |
+
"model.language_model.layers.59.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 744 |
+
"model.language_model.layers.59.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 745 |
+
"model.language_model.layers.59.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
|
| 746 |
+
"model.language_model.layers.59.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
| 747 |
+
"model.language_model.layers.59.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
| 748 |
+
"model.language_model.layers.59.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
|
| 749 |
+
"model.language_model.layers.59.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
| 750 |
+
"model.language_model.layers.59.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
| 751 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 752 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 753 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 754 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 755 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 756 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 757 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 758 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 759 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 760 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 761 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 762 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 763 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 764 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 765 |
+
"model.language_model.layers.60.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 766 |
+
"model.language_model.layers.60.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 767 |
+
"model.language_model.layers.60.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 768 |
+
"model.language_model.layers.60.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 769 |
+
"model.language_model.layers.60.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 770 |
+
"model.language_model.layers.60.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 771 |
+
"model.language_model.layers.60.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 772 |
+
"model.language_model.layers.60.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 773 |
+
"model.language_model.layers.60.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 774 |
+
"model.language_model.layers.60.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 775 |
+
"model.language_model.layers.60.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 776 |
+
"model.language_model.layers.60.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 777 |
+
"model.language_model.layers.60.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 778 |
+
"model.language_model.layers.60.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 779 |
+
"model.language_model.layers.61.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 780 |
+
"model.language_model.layers.61.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 781 |
+
"model.language_model.layers.61.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 782 |
+
"model.language_model.layers.61.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 783 |
+
"model.language_model.layers.61.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 784 |
+
"model.language_model.layers.61.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 785 |
+
"model.language_model.layers.61.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 786 |
+
"model.language_model.layers.61.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 787 |
+
"model.language_model.layers.61.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 788 |
+
"model.language_model.layers.61.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 789 |
+
"model.language_model.layers.61.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 790 |
+
"model.language_model.layers.61.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
| 791 |
+
"model.language_model.layers.61.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
| 792 |
+
"model.language_model.layers.61.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 793 |
+
"model.language_model.layers.62.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 794 |
+
"model.language_model.layers.62.linear_attn.A_log": "model-00012-of-00012.safetensors",
|
| 795 |
+
"model.language_model.layers.62.linear_attn.conv1d.weight": "model-00012-of-00012.safetensors",
|
| 796 |
+
"model.language_model.layers.62.linear_attn.dt_bias": "model-00012-of-00012.safetensors",
|
| 797 |
+
"model.language_model.layers.62.linear_attn.in_proj_a.weight": "model-00012-of-00012.safetensors",
|
| 798 |
+
"model.language_model.layers.62.linear_attn.in_proj_b.weight": "model-00012-of-00012.safetensors",
|
| 799 |
+
"model.language_model.layers.62.linear_attn.in_proj_qkv.weight": "model-00012-of-00012.safetensors",
|
| 800 |
+
"model.language_model.layers.62.linear_attn.in_proj_z.weight": "model-00012-of-00012.safetensors",
|
| 801 |
+
"model.language_model.layers.62.linear_attn.norm.weight": "model-00012-of-00012.safetensors",
|
| 802 |
+
"model.language_model.layers.62.linear_attn.out_proj.weight": "model-00012-of-00012.safetensors",
|
| 803 |
+
"model.language_model.layers.62.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
| 804 |
+
"model.language_model.layers.62.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
| 805 |
+
"model.language_model.layers.62.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
| 806 |
+
"model.language_model.layers.62.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 807 |
+
"model.language_model.layers.63.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 808 |
+
"model.language_model.layers.63.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
| 809 |
+
"model.language_model.layers.63.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
| 810 |
+
"model.language_model.layers.63.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
| 811 |
+
"model.language_model.layers.63.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 812 |
+
"model.language_model.layers.63.self_attn.k_norm.weight": "model-00012-of-00012.safetensors",
|
| 813 |
+
"model.language_model.layers.63.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
| 814 |
+
"model.language_model.layers.63.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
| 815 |
+
"model.language_model.layers.63.self_attn.q_norm.weight": "model-00012-of-00012.safetensors",
|
| 816 |
+
"model.language_model.layers.63.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
| 817 |
+
"model.language_model.layers.63.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
| 818 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 819 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 820 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 821 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 822 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 823 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
|
| 824 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
| 825 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
| 826 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
|
| 827 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
| 828 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
| 829 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 830 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 831 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 832 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 833 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 834 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 835 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 836 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 837 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 838 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 839 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 840 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 841 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 842 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 843 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 844 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 845 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 846 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 847 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 848 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 849 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 850 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 851 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 852 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 853 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 854 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 855 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 856 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 857 |
+
"model.language_model.norm.weight": "model-00012-of-00012.safetensors"
|
| 858 |
+
}
|
| 859 |
+
}
|
darwin-28r/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
darwin-28r/tokenizer_config.json
ADDED
|
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|vision_pad|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>",
|
| 33 |
+
"added_tokens_decoder": {
|
| 34 |
+
"248044": {
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
"248045": {
|
| 43 |
+
"content": "<|im_start|>",
|
| 44 |
+
"single_word": false,
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"special": true
|
| 49 |
+
},
|
| 50 |
+
"248046": {
|
| 51 |
+
"content": "<|im_end|>",
|
| 52 |
+
"single_word": false,
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"rstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"special": true
|
| 57 |
+
},
|
| 58 |
+
"248047": {
|
| 59 |
+
"content": "<|object_ref_start|>",
|
| 60 |
+
"single_word": false,
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"special": true
|
| 65 |
+
},
|
| 66 |
+
"248048": {
|
| 67 |
+
"content": "<|object_ref_end|>",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
"248049": {
|
| 75 |
+
"content": "<|box_start|>",
|
| 76 |
+
"single_word": false,
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"rstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"special": true
|
| 81 |
+
},
|
| 82 |
+
"248050": {
|
| 83 |
+
"content": "<|box_end|>",
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"rstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"special": true
|
| 89 |
+
},
|
| 90 |
+
"248051": {
|
| 91 |
+
"content": "<|quad_start|>",
|
| 92 |
+
"single_word": false,
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"rstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"special": true
|
| 97 |
+
},
|
| 98 |
+
"248052": {
|
| 99 |
+
"content": "<|quad_end|>",
|
| 100 |
+
"single_word": false,
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"rstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"special": true
|
| 105 |
+
},
|
| 106 |
+
"248053": {
|
| 107 |
+
"content": "<|vision_start|>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
"248054": {
|
| 115 |
+
"content": "<|vision_end|>",
|
| 116 |
+
"single_word": false,
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"rstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"special": true
|
| 121 |
+
},
|
| 122 |
+
"248055": {
|
| 123 |
+
"content": "<|vision_pad|>",
|
| 124 |
+
"single_word": false,
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"special": true
|
| 129 |
+
},
|
| 130 |
+
"248056": {
|
| 131 |
+
"content": "<|image_pad|>",
|
| 132 |
+
"single_word": false,
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"rstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"special": true
|
| 137 |
+
},
|
| 138 |
+
"248057": {
|
| 139 |
+
"content": "<|video_pad|>",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": true
|
| 145 |
+
},
|
| 146 |
+
"248058": {
|
| 147 |
+
"content": "<tool_call>",
|
| 148 |
+
"single_word": false,
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"rstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"special": false
|
| 153 |
+
},
|
| 154 |
+
"248059": {
|
| 155 |
+
"content": "</tool_call>",
|
| 156 |
+
"single_word": false,
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"rstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"special": false
|
| 161 |
+
},
|
| 162 |
+
"248060": {
|
| 163 |
+
"content": "<|fim_prefix|>",
|
| 164 |
+
"single_word": false,
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"rstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"special": false
|
| 169 |
+
},
|
| 170 |
+
"248061": {
|
| 171 |
+
"content": "<|fim_middle|>",
|
| 172 |
+
"single_word": false,
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"rstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"special": false
|
| 177 |
+
},
|
| 178 |
+
"248062": {
|
| 179 |
+
"content": "<|fim_suffix|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": false
|
| 185 |
+
},
|
| 186 |
+
"248063": {
|
| 187 |
+
"content": "<|fim_pad|>",
|
| 188 |
+
"single_word": false,
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"rstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"special": false
|
| 193 |
+
},
|
| 194 |
+
"248064": {
|
| 195 |
+
"content": "<|repo_name|>",
|
| 196 |
+
"single_word": false,
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"rstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"special": false
|
| 201 |
+
},
|
| 202 |
+
"248065": {
|
| 203 |
+
"content": "<|file_sep|>",
|
| 204 |
+
"single_word": false,
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"rstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"special": false
|
| 209 |
+
},
|
| 210 |
+
"248066": {
|
| 211 |
+
"content": "<tool_response>",
|
| 212 |
+
"single_word": false,
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"special": false
|
| 217 |
+
},
|
| 218 |
+
"248067": {
|
| 219 |
+
"content": "</tool_response>",
|
| 220 |
+
"single_word": false,
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"rstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"special": false
|
| 225 |
+
},
|
| 226 |
+
"248068": {
|
| 227 |
+
"content": "<think>",
|
| 228 |
+
"single_word": false,
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"rstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"special": false
|
| 233 |
+
},
|
| 234 |
+
"248069": {
|
| 235 |
+
"content": "</think>",
|
| 236 |
+
"single_word": false,
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"rstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"special": false
|
| 241 |
+
},
|
| 242 |
+
"248070": {
|
| 243 |
+
"content": "<|audio_start|>",
|
| 244 |
+
"single_word": false,
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"rstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"special": true
|
| 249 |
+
},
|
| 250 |
+
"248071": {
|
| 251 |
+
"content": "<|audio_end|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
"248072": {
|
| 259 |
+
"content": "<tts_pad>",
|
| 260 |
+
"single_word": false,
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"rstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"special": true
|
| 265 |
+
},
|
| 266 |
+
"248073": {
|
| 267 |
+
"content": "<tts_text_bos>",
|
| 268 |
+
"single_word": false,
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"rstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"special": true
|
| 273 |
+
},
|
| 274 |
+
"248074": {
|
| 275 |
+
"content": "<tts_text_eod>",
|
| 276 |
+
"single_word": false,
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"rstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"special": true
|
| 281 |
+
},
|
| 282 |
+
"248075": {
|
| 283 |
+
"content": "<tts_text_bos_single>",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"special": true
|
| 289 |
+
},
|
| 290 |
+
"248076": {
|
| 291 |
+
"content": "<|audio_pad|>",
|
| 292 |
+
"single_word": false,
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"rstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"special": true
|
| 297 |
+
}
|
| 298 |
+
},
|
| 299 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n<think>\n' }}\n{%- endif %}"
|
| 300 |
+
}
|
darwin-28r/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0945b05f2e8d742e8dc558fa8834470035458c40da8277b79a130aabc0736603
|
| 3 |
+
size 5265
|