Instructions to use ritog/robi-kobi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ritog/robi-kobi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ritog/robi-kobi")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ritog/robi-kobi") model = AutoModelForCausalLM.from_pretrained("ritog/robi-kobi") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ritog/robi-kobi with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ritog/robi-kobi" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ritog/robi-kobi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ritog/robi-kobi
- SGLang
How to use ritog/robi-kobi 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 "ritog/robi-kobi" \ --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": "ritog/robi-kobi", "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 "ritog/robi-kobi" \ --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": "ritog/robi-kobi", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ritog/robi-kobi with Docker Model Runner:
docker model run hf.co/ritog/robi-kobi
Commit History
back to the old tokenizer bec9a7f
Ritobrata Ghosh commited on
tokenizer.json from ghosh-r/bangla-gpt2 d5a5f9c
Ritobrata Ghosh commited on
Update README.md 677ab6d
Update README.md 2ae2679
Create README.md 04045de
adding tokenizer files 3e13fb8
Ritobrata Ghosh commited on
initial commit b4ff52e
Ritobrata Ghosh commited on