Instructions to use AgentPublic/Faust with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AgentPublic/Faust with Transformers:

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

pipe = pipeline("text-generation", model="AgentPublic/Faust")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AgentPublic/Faust")
model = AutoModelForCausalLM.from_pretrained("AgentPublic/Faust")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AgentPublic/Faust with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AgentPublic/Faust

SGLang

How to use AgentPublic/Faust 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 "AgentPublic/Faust" \
    --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": "AgentPublic/Faust",
		"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 "AgentPublic/Faust" \
        --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": "AgentPublic/Faust",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AgentPublic/Faust with Docker Model Runner:
```
docker model run hf.co/AgentPublic/Faust
```

pedevineau commited on Nov 6, 2023

Commit

1df5d40

1 Parent(s): 47df78c

Fix typo

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ language:
 library_name: transformers
 pipeline_tag: text-generation
 ---
-French chat model based on Mistral-Hermes and trained on answers from servicespublics.fr and synthetic questions.
 The syntax is based on chatml and should be used this way.
 > <|im_start|>system\nTu es Félix, le chatbot des services publics français. Tu dois apporter une réponse courtoise à la question qui t'es posée en utilisant un language précis et administratif<|im_end|>\n<|im_start|>user\n[Question]<|im_end|>\n<|im_start|>assistant\n

 library_name: transformers
 pipeline_tag: text-generation
 ---
+French chat model based on Mistral-Hermes and trained on answers from service-public.fr and synthetic questions.
 The syntax is based on chatml and should be used this way.
 > <|im_start|>system\nTu es Félix, le chatbot des services publics français. Tu dois apporter une réponse courtoise à la question qui t'es posée en utilisant un language précis et administratif<|im_end|>\n<|im_start|>user\n[Question]<|im_end|>\n<|im_start|>assistant\n