Instructions to use Equall/SaulLM-54-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Equall/SaulLM-54-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Equall/SaulLM-54-Base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Equall/SaulLM-54-Base") model = AutoModelForCausalLM.from_pretrained("Equall/SaulLM-54-Base") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Equall/SaulLM-54-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Equall/SaulLM-54-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Equall/SaulLM-54-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Equall/SaulLM-54-Base
- SGLang
How to use Equall/SaulLM-54-Base 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 "Equall/SaulLM-54-Base" \ --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": "Equall/SaulLM-54-Base", "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 "Equall/SaulLM-54-Base" \ --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": "Equall/SaulLM-54-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Equall/SaulLM-54-Base with Docker Model Runner:
docker model run hf.co/Equall/SaulLM-54-Base
Update README.md
Browse files
README.md
CHANGED
|
@@ -57,13 +57,14 @@ SaulLM-54B was trained on a rich dataset comprising European and US legal texts,
|
|
| 57 |
To reference SaulLM-54B in your work, please cite this model card.
|
| 58 |
|
| 59 |
```
|
| 60 |
-
@misc{
|
| 61 |
-
title={SaulLM-54B
|
| 62 |
-
author={
|
| 63 |
year={2024},
|
| 64 |
-
eprint={
|
| 65 |
archivePrefix={arXiv},
|
| 66 |
-
primaryClass={cs.CL}
|
|
|
|
| 67 |
}
|
| 68 |
```
|
| 69 |
|
|
|
|
| 57 |
To reference SaulLM-54B in your work, please cite this model card.
|
| 58 |
|
| 59 |
```
|
| 60 |
+
@misc{colombo2024saullm54bsaullm141bscaling,
|
| 61 |
+
title={SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain},
|
| 62 |
+
author={Pierre Colombo and Telmo Pires and Malik Boudiaf and Rui Melo and Dominic Culver and Sofia Morgado and Etienne Malaboeuf and Gabriel Hautreux and Johanne Charpentier and Michael Desa},
|
| 63 |
year={2024},
|
| 64 |
+
eprint={2407.19584},
|
| 65 |
archivePrefix={arXiv},
|
| 66 |
+
primaryClass={cs.CL},
|
| 67 |
+
url={https://arxiv.org/abs/2407.19584},
|
| 68 |
}
|
| 69 |
```
|
| 70 |
|