Instructions to use yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit with Transformers:

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

pipe = pipeline("text-generation", model="yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit")
model = AutoModelForCausalLM.from_pretrained("yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit")
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 yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit

SGLang

How to use yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit 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 "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit" \
    --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": "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit",
		"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 "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit" \
        --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": "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit with Docker Model Runner:
```
docker model run hf.co/yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit
```

Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit

This repository contains a W2A16 OmniQuant checkpoint derived from meta-llama/Meta-Llama-3.1-8B-Instruct.

Quantization configuration

Method: OmniQuant
Weight precision: 2-bit
Activation precision: 16-bit
Group size: 128
Optimization epochs: 40
Learnable weight clipping (LWC): enabled
Learnable equivalent transformation (LET): disabled
Calibration dataset: C4 English validation split
Calibration samples: 128
Calibration sequence length: 512
Calibration seed: 42

Evaluation

Dataset	Split	Sequence length	Perplexity
WikiText2	test	2048	671.2557

The evaluation used the full tokenized WikiText2 test corpus with non-overlapping 2048-token windows.

Checkpoint format

This follows OmniQuant's fake-quantized Hugging Face save path. It is not a packed low-bit runtime checkpoint, so its storage and loading memory can remain close to FP16 despite representing W2A16 quantized weights.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

Transformers may report unused weight_quantizer.scales and weight_quantizer.zeros entries when loading. The fake-quantized model weights still load through the standard Transformers path used for the reported PPL.

License

Use of this checkpoint is subject to the license and terms of the base model.

Downloads last month: 52

Safetensors

Model size

8B params

Tensor type

F16

Model tree for yw223/Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2852)

this model

yw223
/

Meta-Llama-3.1-8B-Instruct-OmniQuant-2bit