Text Generation
Transformers
PyTorch
llama
conversational
text-generation-inference
4-bit precision
awq
Instructions to use Everlyn/llama3-8b-w4-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Everlyn/llama3-8b-w4-awq with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Everlyn/llama3-8b-w4-awq") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Everlyn/llama3-8b-w4-awq") model = AutoModelForCausalLM.from_pretrained("Everlyn/llama3-8b-w4-awq", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Everlyn/llama3-8b-w4-awq with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Everlyn/llama3-8b-w4-awq" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Everlyn/llama3-8b-w4-awq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Everlyn/llama3-8b-w4-awq
- SGLang
How to use Everlyn/llama3-8b-w4-awq 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 "Everlyn/llama3-8b-w4-awq" \ --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": "Everlyn/llama3-8b-w4-awq", "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 "Everlyn/llama3-8b-w4-awq" \ --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": "Everlyn/llama3-8b-w4-awq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Everlyn/llama3-8b-w4-awq with Docker Model Runner:
docker model run hf.co/Everlyn/llama3-8b-w4-awq
Download pytorch_model.bin from Everlyn/llama3-8b-w4-awq: direct link, hf CLI and curl.
- Browser
- Download file 5.81 GB
-
https://huggingface.co/Everlyn/llama3-8b-w4-awq/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://Everlyn/llama3-8b-w4-awq/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/Everlyn/llama3-8b-w4-awq/resolve/main/pytorch_model.bin
5.81 GB
- Xet hash:
- c250823f14d4da7fbf6d294428fc4f4aca941e2f78786af27332f7c7b9a75f26
- Size of remote file:
- 5.81 GB
- SHA256:
- 4c4d50403d6a93ad187f989a456488cc45c0afa17b1859d97fd34f39d6453e41
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.