Instructions to use 01-ai/Yi-1.5-9B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 01-ai/Yi-1.5-9B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="01-ai/Yi-1.5-9B-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-1.5-9B-Chat")
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-1.5-9B-Chat")
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 01-ai/Yi-1.5-9B-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "01-ai/Yi-1.5-9B-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "01-ai/Yi-1.5-9B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/01-ai/Yi-1.5-9B-Chat

SGLang

How to use 01-ai/Yi-1.5-9B-Chat 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 "01-ai/Yi-1.5-9B-Chat" \
    --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": "01-ai/Yi-1.5-9B-Chat",
		"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 "01-ai/Yi-1.5-9B-Chat" \
        --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": "01-ai/Yi-1.5-9B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 01-ai/Yi-1.5-9B-Chat with Docker Model Runner:
```
docker model run hf.co/01-ai/Yi-1.5-9B-Chat
```

Please add prompt template to Readme for gguf.

by ayyylol - opened May 12, 2024

Discussion

ayyylol

May 12, 2024

Thank you for this model!

I was wondering what the prompt template is?

-p "Hello" makes it only go into completion mode, unfortunately.

lorinma

01-ai org May 12, 2024

check tokenizer config, standard chatML format

cstr

May 12, 2024

•

edited May 12, 2024

should be chatml, but from the config, it looks awkward with regard to the system prompt, maybe they meant it like:

<|startoftext|>You are a helpful, polite AI assistant.<|im_end|>
<|im_start|>user
What is the meaning of life?<|im_end|>
<|im_start|>assistant

MoonRide

May 12, 2024

•

edited May 13, 2024

Something might be wrong with either tokenizer, or llama.cpp - "<|im_end|> " is being displayed as text during the chat:

Steps:

convert-hf-to-gguf.py --outtype f16 ..\Yi-1.5-9B-Chat\ --outfile Yi-1.5-9B-Chat-F16.gguf
quantize Yi-1.5-9B-Chat-F16.gguf Yi-1.5-9B-Chat-Q6_K.gguf Q6_K
server -v -ngl 99 -m Yi-1.5-9B-Chat-Q6_K.gguf -c 4096
http://localhost:8080/, changed user name to "user", bot name to "assistant", prompt to "You're a helpful assistant.".

GGUF and test made using current-ish llama.cpp (b2859).

UPDATE: using different name than assistant doesn't cause this problem:

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