Instructions to use jeiku/Rosa_v3_3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jeiku/Rosa_v3_3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jeiku/Rosa_v3_3B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("jeiku/Rosa_v3_3B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jeiku/Rosa_v3_3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jeiku/Rosa_v3_3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jeiku/Rosa_v3_3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jeiku/Rosa_v3_3B
- SGLang
How to use jeiku/Rosa_v3_3B 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 "jeiku/Rosa_v3_3B" \ --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": "jeiku/Rosa_v3_3B", "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 "jeiku/Rosa_v3_3B" \ --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": "jeiku/Rosa_v3_3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jeiku/Rosa_v3_3B with Docker Model Runner:
docker model run hf.co/jeiku/Rosa_v3_3B
This model is pretty much the pinnacle of what I can achieve in this class. I used my v2 merge as a base, then finetuned three models over the v2 base using custom datasets. I then merged the resultant models with the dare ties method.
This is intended to serve as my AI companion and you may not like some of my tuning.
GGUF available here: https://huggingface.co/jeiku/Rosa_v3_3B_GGUF
- Downloads last month
- 8