Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,32 @@
+---
+license: llama3
+base_model: meta-llama/Llama-4-Scout-17B-16E
+tags:
+- llama4
+- moe
+- torchtitan
+- custom
+---
+
+# Llama 4 Debug Model - Trained with TorchTitan
+
+Custom-trained Llama 4 model using TorchTitan framework.
+
+## Model Details
+
+- **Training Framework**: TorchTitan
+- **Training Steps**: 10,000
+- **Model Size**: ~220 MB
+- **Precision**: bfloat16
+
+## Usage
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("lakhera2023/llama4-debugmodel-10k")
+tokenizer = AutoTokenizer.from_pretrained("lakhera2023/llama4-debugmodel-10k")
+
+prompt = "Once upon a time"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(outputs[0]))

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a67862d9623ab17d348d4640edc8f8e42f35fa5aeaeeb7f8d2039056cfb638
+size 231303471

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c680f67931b83232a1d9dd880f15ff671173515fae2d3cd607bbc81bec894c7
+size 231302968

model.safetensors.index.json

@@ -0,0 +1,64 @@
+{
+  "metadata": {
+    "total_size": 231295488
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.feed_forward.experts.down_proj": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.feed_forward.router.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.feed_forward.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.feed_forward.experts.down_proj": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.feed_forward.router.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.feed_forward.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.feed_forward.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.feed_forward.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.feed_forward.experts.down_proj": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.feed_forward.router.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.feed_forward.shared_expert.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.feed_forward.shared_expert.down_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.feed_forward.shared_expert.up_proj.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.norm.weight": "model-00001-of-00001.safetensors",
+    "language_model.lm_head.weight": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.1.feed_forward.experts.gate_up_proj": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.3.feed_forward.experts.gate_up_proj": "model-00001-of-00001.safetensors",
+    "language_model.model.layers.5.feed_forward.experts.gate_up_proj": "model-00001-of-00001.safetensors"
+  }
+}

sharded/shard-00001-model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e704adfdbefd8340f462adeb1ff85063a7dad69cf32c58e67bb8649941cbfcd
+size 231308256

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot|>",
+  "pad_token": "<|finetune_right_pad|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
+size 27948578

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bdbaf59b0762c8c807617e2d8ea51420eb1b1de266df2495be755c8e0ed6ed
+size 3622230