Instructions to use bharatgenai/Param-1-2.9B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bharatgenai/Param-1-2.9B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="bharatgenai/Param-1-2.9B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("bharatgenai/Param-1-2.9B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bharatgenai/Param-1-2.9B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bharatgenai/Param-1-2.9B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bharatgenai/Param-1-2.9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bharatgenai/Param-1-2.9B-Instruct

SGLang

How to use bharatgenai/Param-1-2.9B-Instruct 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 "bharatgenai/Param-1-2.9B-Instruct" \
    --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": "bharatgenai/Param-1-2.9B-Instruct",
		"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 "bharatgenai/Param-1-2.9B-Instruct" \
        --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": "bharatgenai/Param-1-2.9B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bharatgenai/Param-1-2.9B-Instruct with Docker Model Runner:
```
docker model run hf.co/bharatgenai/Param-1-2.9B-Instruct
```

HF compatible weights and license?

by adarshxs - opened Jun 7, 2025

Discussion

adarshxs

Jun 7, 2025

Any plans on releasing huggingface compatible weights? Are these weights MIT or non commercial licensed? Very confusing since you've got MIT licensing and responsibility and a custom non commercial in the last section. I don't see any base model weight so assuming this is non commercial?

kundeshwar20

BharatGen AI org Jul 17, 2025

Hi! Yes, the Hugging Face-compatible weights are released — you can find them in the same repo
The code is MIT-licensed, but the model weights are under a non-commercial license

Neural-Hacker

Oct 9, 2025

Hi team! I've run into an issue trying to load your model directly on Kaggle or Colab from Hugging Face. It seems like I have to manually download every file (like the model.safetensors) before I can use it. Please look into making these models loadable directly? Thanks

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment