Instructions to use Equall/Saul-7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Equall/Saul-7B-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Equall/Saul-7B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Equall/Saul-7B-Base")
model = AutoModelForCausalLM.from_pretrained("Equall/Saul-7B-Base", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Equall/Saul-7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Equall/Saul-7B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Equall/Saul-7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Equall/Saul-7B-Base

SGLang

How to use Equall/Saul-7B-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/Saul-7B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Equall/Saul-7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Saul-7B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Equall/Saul-7B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Equall/Saul-7B-Base with Docker Model Runner:
```
docker model run hf.co/Equall/Saul-7B-Base
```

PierreColombo commited on Mar 10, 2024

Commit

4a6f144

verified ·

1 Parent(s): cd3d59a

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -6

README.md CHANGED Viewed

@@ -1,11 +1,15 @@
 ---
 library_name: transformers
-tags: []
 ---
-# SaulLM-7B-Base
-The base model for SaulLM-7B, a large language model tailored for Legal domain. This model is obtained by continue pretraining of Mistral-7B.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644a900e3a619fe72b14af0f/OU4Y3s-WckYKMN4fQkNiS.png)
@@ -22,7 +26,6 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Model type:** 7B
 - **Language(s) (NLP):** English
 - **License:** MIT
-- **Finetuned from model:** Check Saul-7B-Instruct
 ### Model Sources
@@ -46,7 +49,7 @@ Here's how you can run the model using the pipeline() function from 🤗 Transfo
 import torch
 from transformers import pipeline
-pipe = pipeline("text-generation", model="Equall/Saul-Base", torch_dtype=torch.bfloat16, device_map="auto")
 # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
 messages = [
     {"role": "user", "content": "[YOUR QUERY GOES HERE]"},
@@ -65,6 +68,9 @@ This model is built upon the technology of LLM, which comes with inherent limita
 ## Citation
 ```bibtex
@@ -76,4 +82,4 @@ This model is built upon the technology of LLM, which comes with inherent limita
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```

 ---
 library_name: transformers
+tags:
+- legal
+license: mit
+language:
+- en
 ---
+# Equall/Saul-Base-v1
+This is the base model for Equall/Saul-Base, a large instruct language model tailored for Legal domain. This model is obtained by continue pretraining of Mistral-7B.
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/644a900e3a619fe72b14af0f/OU4Y3s-WckYKMN4fQkNiS.png)
 - **Model type:** 7B
 - **Language(s) (NLP):** English
 - **License:** MIT
 ### Model Sources
 import torch
 from transformers import pipeline
+pipe = pipeline("text-generation", model="Equall/Saul-Instruct-v1", torch_dtype=torch.bfloat16, device_map="auto")
 # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
 messages = [
     {"role": "user", "content": "[YOUR QUERY GOES HERE]"},
 ## Citation
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+**BibTeX:**
 ```bibtex
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
+```