Instructions to use fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-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-3.1-8B-Instruct-auto_round-int8-gs128-sym")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym")
model = AutoModelForCausalLM.from_pretrained("fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-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-3.1-8B-Instruct-auto_round-int8-gs128-sym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym

SGLang

How to use fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-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-3.1-8B-Instruct-auto_round-int8-gs128-sym" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-3.1-8B-Instruct-auto_round-int8-gs128-sym" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym
```

Model Information

Quantized version of meta-llama/Llama-3.1-8B-Instruct using torch.float32 for quantization tuning.

8 bits (INT8)
group size = 128
Symmetrical Quantization
Method WoQ (AutoRound format)

Fast and low memory, 2-3X speedup (slight accuracy drop at W8G128)

Quantization framework: Intel AutoRound v0.4.5

Note: this INT8 version of Llama-3.1-8B-Instruct has been quantized to run inference through CPU.

Replication Recipe

Step 1 Install Requirements

I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.

wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.5.tar.gz
tar -xvzf v0.4.5.tar.gz
cd auto-round-0.4.5
pip install -r requirements-cpu.txt --upgrade

Step 2 Build Intel AutoRound wheel from sources

pip install -vvv --no-build-isolation -e .[cpu]

Step 3 Script for Quantization

  from transformers import AutoModelForCausalLM, AutoTokenizer
  model_name = "meta-llama/Llama-3.1-8B-Instruct"
  model = AutoModelForCausalLM.from_pretrained(model_name)
  tokenizer = AutoTokenizer.from_pretrained(model_name)
  from auto_round import AutoRound
  bits, group_size, sym, device = 8, 128, True, 'cpu'
  autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device)
  autoround.quantize()
  output_dir = "./AutoRound/meta-llama_Llama-3.1-8B-Instruct-auto_round-int8-gs128-sym"
  autoround.save_quantized(output_dir, format='auto_round', inplace=True)