Instructions to use mangal-singh-boipai/Mangal-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mangal-singh-boipai/Mangal-AI with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "mangal-singh-boipai/Mangal-AI")

Transformers

How to use mangal-singh-boipai/Mangal-AI with Transformers:

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

pipe = pipeline("text-generation", model="mangal-singh-boipai/Mangal-AI")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mangal-singh-boipai/Mangal-AI", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mangal-singh-boipai/Mangal-AI with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mangal-singh-boipai/Mangal-AI

SGLang

How to use mangal-singh-boipai/Mangal-AI 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 "mangal-singh-boipai/Mangal-AI" \
    --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": "mangal-singh-boipai/Mangal-AI",
		"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 "mangal-singh-boipai/Mangal-AI" \
        --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": "mangal-singh-boipai/Mangal-AI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use mangal-singh-boipai/Mangal-AI with Docker Model Runner:
```
docker model run hf.co/mangal-singh-boipai/Mangal-AI
```

Mangal-AI

Made by Mangal Singh Boipai from Gidbasa, Chaibasa, District West Singhbhum, Jharkhand, India.

Jharkhand ka pehla Llama-3 LoRA Model! 🇮🇳

Details

Base Model: unsloth/llama-3-8b-bnb-4bit
From: Gidbasa, Chaibasa, West Singhbhum, Jharkhand
Language: Hindi, Ho, Hinglish, English

Johar Jharkhand!

Downloads last month: 14

Model tree for mangal-singh-boipai/Mangal-AI

Base model

meta-llama/Meta-Llama-3-8B

Quantized

unsloth/llama-3-8b-bnb-4bit

Adapter

(312)

this model