Instructions to use Cognute02/llama_3_1_8B_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cognute02/llama_3_1_8B_4bit with Transformers:

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

pipe = pipeline("text-generation", model="Cognute02/llama_3_1_8B_4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cognute02/llama_3_1_8B_4bit")
model = AutoModelForCausalLM.from_pretrained("Cognute02/llama_3_1_8B_4bit", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Cognute02/llama_3_1_8B_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cognute02/llama_3_1_8B_4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cognute02/llama_3_1_8B_4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Cognute02/llama_3_1_8B_4bit

SGLang

How to use Cognute02/llama_3_1_8B_4bit 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 "Cognute02/llama_3_1_8B_4bit" \
    --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": "Cognute02/llama_3_1_8B_4bit",
		"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 "Cognute02/llama_3_1_8B_4bit" \
        --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": "Cognute02/llama_3_1_8B_4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Cognute02/llama_3_1_8B_4bit 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 Cognute02/llama_3_1_8B_4bit 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 Cognute02/llama_3_1_8B_4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Cognute02/llama_3_1_8B_4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Cognute02/llama_3_1_8B_4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use Cognute02/llama_3_1_8B_4bit with Docker Model Runner:
```
docker model run hf.co/Cognute02/llama_3_1_8B_4bit
```

llama_3_1_8B_4bit / handler.py

sundeepsingh01

Update handler.py

76e0eed verified almost 2 years ago

Raw

History Blame Contribute Delete

1.42 kB

	from typing import Dict, List, Any
	from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
	from langchain_huggingface import HuggingFacePipeline, ChatHuggingFace, HuggingFaceEndpoint
	import torch
	from huggingface_hub import login

	api_key = 'hf'+ '_' + 'tlVzheuQBwjAxOtNKPqnHSQprFYnDLllut'
	login(token=api_key)

	class EndpointHandler:
	def __init__(self, path1="Cognute02/llama_3_1_8B_4bit"):
	# load model and processor from path
	quantization_config = BitsAndBytesConfig(
	load_in_4bit=True,
	bnb_4bit_quant_type="nf4",
	bnb_4bit_compute_dtype="float16",
	bnb_4bit_use_double_quant=True,
	)

	llm = HuggingFacePipeline.from_model_id(
	model_id=path1,
	task="text-generation",
	pipeline_kwargs=dict(
	max_new_tokens=512,
	do_sample=False,
	repetition_penalty=1.03,
	return_full_text=False,
	temperature = 0.25
	),
	model_kwargs={"quantization_config": quantization_config},
	)

	self.chatllm = ChatHuggingFace(llm=llm)

	def __call__(self, data):
	inputs = data['inputs']
	tools = data['tools']
	llm_ = self.chatllm.bind_tools(tools)
	outputs = llm_.invoke(inputs)
	return outputs