Instructions to use Equall/Saul-7B-Instruct-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Equall/Saul-7B-Instruct-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Equall/Saul-7B-Instruct-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Equall/Saul-7B-Instruct-v1")
model = AutoModelForCausalLM.from_pretrained("Equall/Saul-7B-Instruct-v1")
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
Local Apps Settings

vLLM

How to use Equall/Saul-7B-Instruct-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Equall/Saul-7B-Instruct-v1"
# 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-Instruct-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Equall/Saul-7B-Instruct-v1

SGLang

How to use Equall/Saul-7B-Instruct-v1 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-Instruct-v1" \
    --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-Instruct-v1",
		"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-Instruct-v1" \
        --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-Instruct-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Equall/Saul-7B-Instruct-v1 with Docker Model Runner:
```
docker model run hf.co/Equall/Saul-7B-Instruct-v1
```

Prompt Template

by LouisSF - opened Mar 11, 2024

Discussion

LouisSF

Mar 11, 2024

Hi, thank you for the model !
Was it trained using a specific prompt which we should replicate for a non-chat case. For adding system prompts or just text completion.
I was thinking of the original mistral prompt format: <s>[INST] {prompt} [/INST], is this correct ?

PierreColombo

Equall org Mar 11, 2024

Yes any issues ?

PierreColombo changed discussion status to closed Apr 15, 2024

sirrosendo

May 1, 2024

Jingni393

Jul 12, 2024

Is it necessary to use the tokenizer's chat template (according to the model card)? Can I use the prompt format mentioned by Louis: ~~[INST] {prompt} [/INST]?~~

sirrosendo

Sep 21, 2024

Okay I'm going to put it out there has anyone thought of we need to find a way to make these llms less susceptible to malicious content at this point no one currently can be held liable for what an llm outputs when it comes to being fine-tuned but a certain point we will be held accountable for this and so we have to make sure that we prevent an llm from outputting dangerous content.

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