Instructions to use felipeoes/cocoruta-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use felipeoes/cocoruta-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="felipeoes/cocoruta-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("felipeoes/cocoruta-7b") model = AutoModelForCausalLM.from_pretrained("felipeoes/cocoruta-7b") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use felipeoes/cocoruta-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "felipeoes/cocoruta-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "felipeoes/cocoruta-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/felipeoes/cocoruta-7b
- SGLang
How to use felipeoes/cocoruta-7b 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 "felipeoes/cocoruta-7b" \ --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": "felipeoes/cocoruta-7b", "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 "felipeoes/cocoruta-7b" \ --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": "felipeoes/cocoruta-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use felipeoes/cocoruta-7b with Docker Model Runner:
docker model run hf.co/felipeoes/cocoruta-7b
Commit History
Delete pytorch_model-00002-of-00003.bin d10411e verified
Delete pytorch_model-00001-of-00003.bin 25b2aaf verified
Upload LlamaForCausalLM 28d18a3 verified
Upload tokenizer 8161e2b verified
chore: update bibtex with paper details and URL 909961f verified
add paper URL 72f9368 verified
Update README.md 30881bc verified
Update README.md d5e52d8 verified
Update README.md 440dd64 verified
Create README.md daa0871 verified
Upload tokenizer 03ff17b
Upload LlamaForCausalLM af7932b
initial commit b2b3e72
Felipe Oliveira commited on