Instructions to use Recag/BharatAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Recag/BharatAI with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Recag/BharatAI", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Recag/BharatAI", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Recag/BharatAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Recag/BharatAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Recag/BharatAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Recag/BharatAI
- SGLang
How to use Recag/BharatAI 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 "Recag/BharatAI" \ --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": "Recag/BharatAI", "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 "Recag/BharatAI" \ --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": "Recag/BharatAI", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Recag/BharatAI with Docker Model Runner:
docker model run hf.co/Recag/BharatAI
| from transformers import PretrainedConfig | |
| class BharatAIConfig(PretrainedConfig): | |
| model_type = "BharatAI" # Change to the appropriate model type name | |
| def __init__( | |
| self, | |
| vocab_size:int=1000, | |
| n_embd:int=384, | |
| n_head:int=4, | |
| n_layer:int=4, | |
| dropout:float=0.2, | |
| **kwargs | |
| ): | |
| self.vocab_size = vocab_size | |
| self.n_embd = n_embd | |
| self.n_head = n_head | |
| self.n_layer = n_layer | |
| self.dropout = dropout | |
| super().__init__(**kwargs) | |