Instructions to use fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym with Transformers:

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

pipe = pipeline("text-generation", model="fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym

SGLang

How to use fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym 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 "fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym" \
    --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": "fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym",
		"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 "fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym" \
        --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": "fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym
```

Model Information

Quantized version of meta-llama/Llama-3.2-3B-Instruct using torch.float32 for quantization tuning.

4 bits (INT4)
group size = 128
Symmetrical Quantization
Algorith method: TEQ (Trainable Equivalent Transformation for Quantization of LLMs)

Quantization framework: Intel Neural Compressor version 3.3.1

Note: this INT4 version of Llama-3.2-3B-Instruct has been quantized to run inference through CPU.

Disclaimer

This quantized model comes with no warrenty. It has been developed experimetally only for research purposes.

This repository only contains contains two files: quantized_model.pt (weights structure) and qconfig.json, and the generated model is a quantized model. It needs to be used in combination with the base model meta-llama/Llama-3.2-3B-Instruct.

Replication Recipe

$ conda create --name neural-compressor-3.3.1 --file requirements_conda_neural-compressor-3.3.1

$ python meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym.py

Run Inference

To run inference you can use fbaldassarri/woq-inference.

python teq_inference.py --base meta-llama/Llama-3.2-3B-Instruct --model_dir ./meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym --weights_file quantized_weight.pt --config_file qconfig.json --prompt "What If you have got superpowers?" --device cpu

Note: You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

License

Llama 3.2 Community License

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1643)

this model

Collection including fbaldassarri/meta-llama_Llama-3.2-3B-Instruct-TEQ-int4-gs128-sym

TEQ-int4-gs128

Collection

[Highly Experimental Quantization] TEQ (Trainable Equivalent Transformation for Weight-only-Quantization of LLMs) • 8 items • Updated May 2, 2025