Instructions to use iduryodhanrao/my-quantized-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iduryodhanrao/my-quantized-llm with Transformers:

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

pipe = pipeline("text-generation", model="iduryodhanrao/my-quantized-llm")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iduryodhanrao/my-quantized-llm")
model = AutoModelForCausalLM.from_pretrained("iduryodhanrao/my-quantized-llm", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iduryodhanrao/my-quantized-llm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iduryodhanrao/my-quantized-llm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iduryodhanrao/my-quantized-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iduryodhanrao/my-quantized-llm

SGLang

How to use iduryodhanrao/my-quantized-llm 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 "iduryodhanrao/my-quantized-llm" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iduryodhanrao/my-quantized-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "iduryodhanrao/my-quantized-llm" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iduryodhanrao/my-quantized-llm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iduryodhanrao/my-quantized-llm with Docker Model Runner:
```
docker model run hf.co/iduryodhanrao/my-quantized-llm
```

my-quantized-llm

This is a quantized version of an LLM model, optimized for efficient inference.

Model Details

Quantization: 4-bit or 8-bit using bitsandbytes
Framework: Transformers
Use Case: Text generation with reduced memory footprint

Usage

Load the model locally

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "iduryodhanrao/my-quantized-llm"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    trust_remote_code=True
)

prompt = "Hello, how are you?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Inference API

You can also use the Hugging Face Inference API:

import requests

API_URL = "https://api-inference.huggingface.co/models/iduryodhanrao/my-quantized-llm"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({"inputs": "The future of AI is"})
print(output)

Limitations

This model is quantized and may have slightly reduced accuracy compared to the original model
Designed for efficient inference rather than fine-tuning

License

Licensed under Apache 2.0

Downloads last month: 10

Safetensors

Model size

0.1B params

Tensor type

F32