Instructions to use HEMASENTHIL/latest_hemallama3.1chatmodel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HEMASENTHIL/latest_hemallama3.1chatmodel with Transformers:

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

pipe = pipeline("text-generation", model="HEMASENTHIL/latest_hemallama3.1chatmodel")
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("HEMASENTHIL/latest_hemallama3.1chatmodel")
model = AutoModelForCausalLM.from_pretrained("HEMASENTHIL/latest_hemallama3.1chatmodel", 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 HEMASENTHIL/latest_hemallama3.1chatmodel with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HEMASENTHIL/latest_hemallama3.1chatmodel"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HEMASENTHIL/latest_hemallama3.1chatmodel",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HEMASENTHIL/latest_hemallama3.1chatmodel

SGLang

How to use HEMASENTHIL/latest_hemallama3.1chatmodel 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 "HEMASENTHIL/latest_hemallama3.1chatmodel" \
    --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": "HEMASENTHIL/latest_hemallama3.1chatmodel",
		"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 "HEMASENTHIL/latest_hemallama3.1chatmodel" \
        --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": "HEMASENTHIL/latest_hemallama3.1chatmodel",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HEMASENTHIL/latest_hemallama3.1chatmodel with Docker Model Runner:
```
docker model run hf.co/HEMASENTHIL/latest_hemallama3.1chatmodel
```

latest_hemallama3.1chatmodel / handler.py

HEMASENTHIL

Upload 2 files

2b1fc3f verified about 2 years ago

Raw History Blame Contribute Delete

1.66 kB

import bitsandbytes as bnb
from transformers import (AutoModelForCausalLM,
                          AutoTokenizer,
                          BitsAndBytesConfig,
                          TrainingArguments,
                          pipeline)
import torch

class EndpointHandler():
    def __init__(self, path=""):
        bnb_config = BitsAndBytesConfig(
            load_in_8bit=True
        )

        model = AutoModelForCausalLM.from_pretrained(
            path,
            device_map="auto",
            torch_dtype="float16",
            quantization_config=bnb_config,
        )

        model.eval()

        tokenizer = AutoTokenizer.from_pretrained(path)
        pipe = pipeline(
            "text-generation",
            model=model,
            tokenizer=tokenizer,
            torch_dtype=torch.float16,
            device_map="auto",
        )
        self.model = model 
        self.tokenizer = tokenizer
        self.pipeline = pipe

    def __call__(self, data) :
        """
        Args:
            data (:obj:):
                includes the input data and the parameters for the inference.
        Return:
            A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
                - "label": A string representing what the label/class is. There can be multiple labels.
                - "score": A score between 0 and 1 describing how confident the model is for this label/class.
        """
        inputs = data.pop("inputs", data)
        parameters = data.pop("parameters", None)
        output = self.pipeline(inputs , **parameters)
        return output

	import bitsandbytes as bnb
	from transformers import (AutoModelForCausalLM,
	AutoTokenizer,
	BitsAndBytesConfig,
	TrainingArguments,
	pipeline)
	import torch

	class EndpointHandler():
	def __init__(self, path=""):
	bnb_config = BitsAndBytesConfig(
	load_in_8bit=True
	)

	model = AutoModelForCausalLM.from_pretrained(
	path,
	device_map="auto",
	torch_dtype="float16",
	quantization_config=bnb_config,
	)

	model.eval()

	tokenizer = AutoTokenizer.from_pretrained(path)
	pipe = pipeline(
	"text-generation",
	model=model,
	tokenizer=tokenizer,
	torch_dtype=torch.float16,
	device_map="auto",
	)
	self.model = model
	self.tokenizer = tokenizer
	self.pipeline = pipe

	def __call__(self, data) :
	"""
	Args:
	data (:obj:):
	includes the input data and the parameters for the inference.
	Return:
	A :obj:`list`:. The object returned should be a list of one list like [[{"label": 0.9939950108528137}]] containing :
	- "label": A string representing what the label/class is. There can be multiple labels.
	- "score": A score between 0 and 1 describing how confident the model is for this label/class.
	"""
	inputs = data.pop("inputs", data)
	parameters = data.pop("parameters", None)
	output = self.pipeline(inputs , **parameters)
	return output