Instructions to use wenbopan/Faro-Yi-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wenbopan/Faro-Yi-9B with Transformers:

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

pipe = pipeline("text-generation", model="wenbopan/Faro-Yi-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wenbopan/Faro-Yi-9B")
model = AutoModelForCausalLM.from_pretrained("wenbopan/Faro-Yi-9B")
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

vLLM

How to use wenbopan/Faro-Yi-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wenbopan/Faro-Yi-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wenbopan/Faro-Yi-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wenbopan/Faro-Yi-9B

SGLang

How to use wenbopan/Faro-Yi-9B 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 "wenbopan/Faro-Yi-9B" \
    --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": "wenbopan/Faro-Yi-9B",
		"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 "wenbopan/Faro-Yi-9B" \
        --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": "wenbopan/Faro-Yi-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wenbopan/Faro-Yi-9B with Docker Model Runner:
```
docker model run hf.co/wenbopan/Faro-Yi-9B
```

Is this same model as "Fi-9B"?

by jfiekdjdk - opened Apr 1, 2024

Discussion

jfiekdjdk

Apr 1, 2024

Hi, I downloaded Fi-9B yesterday, is Faro further finetuned from Fi or just renaming? Thanks!

wenbopan

Owner Apr 1, 2024

Yes. I renamed Fi-9B to Faro-Yi-9B-200K, as I think containing ‘Yi-9B-200K’ in the name is more SEO friendly ;)

However I recommend you to download this model again as today I uploaded the retrained model, which is more stable in terms of stopping generation and overall quality.

jfiekdjdk

Apr 1, 2024

Thanks! I found Fi really good at Chinese document retrieval and summarize in my limited testing, I don't think any Mistral-based finetune can compare.

wenbopan

Owner Apr 1, 2024

Thank you for using my model. Yes I have tried applying Fusang on Mixtral and didn’t get much success. My guess is that Chinese capability has to be learned during pre-training.

wenbopan changed discussion status to closed Apr 2, 2024

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