Instructions to use Equall/SaulLM-54B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Equall/SaulLM-54B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Equall/SaulLM-54B-Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Equall/SaulLM-54B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Equall/SaulLM-54B-Instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Equall/SaulLM-54B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Equall/SaulLM-54B-Instruct"
# 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-54B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Equall/SaulLM-54B-Instruct

SGLang

How to use Equall/SaulLM-54B-Instruct 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-54B-Instruct" \
    --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-54B-Instruct",
		"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-54B-Instruct" \
        --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-54B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Equall/SaulLM-54B-Instruct with Docker Model Runner:
```
docker model run hf.co/Equall/SaulLM-54B-Instruct
```

MMLU-Pro category scores

by yaronr - opened Sep 21, 2024

Discussion

yaronr

Sep 21, 2024

Hi
We ran mmlu-pro on SaulLM-54B-Instruct, and the results below were quite surprising.
We expected SaulLM to ace the law category, but in fact, we saw only 30% correct answers.
Surprisingly, we saw the best mmlu-pro results for SaulLM-54-Instruct for psychology (62%) and biology (66%).
Appreciate your guidance.

We ran vllm latest (0.6.1.post2) with the following params:

--model=Equall/SaulLM-54B-Instruct 
--tensor-parallel-size=2
--pipeline-parallel-size=4
--disable-log-requests
--trust-remote-code
--enable-chunked-prefill
--enable-prefix-caching
--enforce-eager
--max-num-batched-tokens=16384
--max-model-len=8096
--gpu-memory-utilization=0.95

Detailed results per category:

legalcomplex

Sep 21, 2024

Thanks for the useful information, we have a legal LLM, we like to test, can you assist?

yaronr

Sep 22, 2024

@legalcomplex Hey there!
With pleasure!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment