Instructions to use BSC-LT/salamandra-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BSC-LT/salamandra-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BSC-LT/salamandra-7b")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BSC-LT/salamandra-7b") model = AutoModelForCausalLM.from_pretrained("BSC-LT/salamandra-7b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BSC-LT/salamandra-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BSC-LT/salamandra-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BSC-LT/salamandra-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BSC-LT/salamandra-7b
- SGLang
How to use BSC-LT/salamandra-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 "BSC-LT/salamandra-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": "BSC-LT/salamandra-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 "BSC-LT/salamandra-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": "BSC-LT/salamandra-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BSC-LT/salamandra-7b with Docker Model Runner:
docker model run hf.co/BSC-LT/salamandra-7b
Any notes on the new v1.1?
Hi, with the new update of the La Leaderboard, I noticed that Salamandra now scores better than models like Gromenauer, which was not the case a couple of months ago. I guess that the difference in performance is due to the upload of a new model as referenced in the commit log (v1.1). What are the differences? Are there any release notes about it?
Thanks.
Hi Javier,
The models are in a continuous process of improvement. Compared to the last version, the model has been further trained on the same data sources.
Thank you very much for noticing it!
For traceability and fair comparisons, it would be great to at least have a git tag or a note with every release. Thanks for a great model!