Instructions to use afrideva/MiniMA-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/MiniMA-3B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="afrideva/MiniMA-3B-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("afrideva/MiniMA-3B-GGUF", dtype="auto")

llama-cpp-python

How to use afrideva/MiniMA-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/MiniMA-3B-GGUF",
	filename="minima-3b.q2_k.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use afrideva/MiniMA-3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/MiniMA-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/MiniMA-3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/MiniMA-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/MiniMA-3B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf afrideva/MiniMA-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/MiniMA-3B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf afrideva/MiniMA-3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/MiniMA-3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/MiniMA-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/MiniMA-3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/MiniMA-3B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/MiniMA-3B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/MiniMA-3B-GGUF:Q4_K_M

SGLang

How to use afrideva/MiniMA-3B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "afrideva/MiniMA-3B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/MiniMA-3B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "afrideva/MiniMA-3B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/MiniMA-3B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use afrideva/MiniMA-3B-GGUF with Ollama:
```
ollama run hf.co/afrideva/MiniMA-3B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use afrideva/MiniMA-3B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/MiniMA-3B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/MiniMA-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/MiniMA-3B-GGUF to start chatting

Docker Model Runner
How to use afrideva/MiniMA-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/MiniMA-3B-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/MiniMA-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/MiniMA-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniMA-3B-GGUF-Q4_K_M

List all available models

lemonade list

GeneZC/MiniMA-3B-GGUF

Quantized GGUF model files for MiniMA-3B from GeneZC

Name	Quant method	Size
minima-3b.q2_k.gguf	q2_k	1.30 GB
minima-3b.q3_k_m.gguf	q3_k_m	1.51 GB
minima-3b.q4_k_m.gguf	q4_k_m	1.85 GB
minima-3b.q5_k_m.gguf	q5_k_m	2.15 GB
minima-3b.q6_k.gguf	q6_k	2.48 GB
minima-3b.q8_0.gguf	q8_0	3.21 GB

Original Model Card:

MiniMA-3B

📑 arXiv | 🤗 HuggingFace-MiniMA | 🤗 HuggingFace-MiniChat | 🤖 ModelScope-MiniMA | 🤖 ModelScope-MiniChat

❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2.

A language model distilled from an adapted version of LLaMA2-7B following "Towards the Law of Capacity Gap in Distilling Language Models".

Establishing a new compute-performance pareto frontier.

The following is an example code snippet to use MiniMA-3B:

import torch

from transformers import AutoModelForCausalLM, AutoTokenizer

# MiniMA
tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniMA-3B", use_fast=False)
# GPU.
model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-3B", use_cache=True, device_map="auto", torch_dtype=torch.float16).eval()
# CPU.
# model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniMA-3B", use_cache=True, device_map="cpu", torch_dtype=torch.float16).eval()

prompt = "Question: Sherrie tells the truth. Vernell says Sherrie tells the truth. Alexis says Vernell lies. Michaela says Alexis tells the truth. Elanor says Michaela tells the truth. Does Elanor tell the truth?\nAnswer: No\n\nQuestion: Kristian lies. Sherrie says Kristian lies. Delbert says Sherrie lies. Jerry says Delbert tells the truth. Shalonda says Jerry tells the truth. Does Shalonda tell the truth?\nAnswer: No\n\nQuestion: Vina tells the truth. Helene says Vina lies. Kandi says Helene tells the truth. Jamey says Kandi lies. Ka says Jamey lies. Does Ka tell the truth?\nAnswer: No\n\nQuestion: Christie tells the truth. Ka says Christie tells the truth. Delbert says Ka lies. Leda says Delbert tells the truth. Lorine says Leda tells the truth. Does Lorine tell the truth?\nAnswer:"
input_ids = tokenizer([prompt]).input_ids
output_ids = model.generate(
    torch.as_tensor(input_ids).cuda(),
    do_sample=True,
    temperature=0.7,
    max_new_tokens=1024,
)
output_ids = output_ids[0][len(input_ids[0]):]
output = tokenizer.decode(output_ids, skip_special_tokens=True).strip()
# output: "No"

Bibtex

@article{zhang2023law,
    title={Towards the Law of Capacity Gap in Distilling Language Models},
    author={Zhang, Chen and Song, Dawei and Ye, Zheyu and Gao, Yan},
    year={2023},
    url={}
}

Downloads last month: 91

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for afrideva/MiniMA-3B-GGUF

Base model

GeneZC/MiniMA-3B

Quantized

(2)

this model

afrideva
/

MiniMA-3B-GGUF

GeneZC/MiniMA-3B-GGUF

Original Model Card:

MiniMA-3B

Bibtex

Model tree for afrideva/MiniMA-3B-GGUF

Datasets used to train afrideva/MiniMA-3B-GGUF