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

Libraries

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

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

pipe = pipeline("text-generation", model="01-ai/Yi-Coder-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-Coder-9B-Chat")
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-Coder-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-Coder-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-Coder-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-Coder-9B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Interested why you're comparing it with deepseek coder v1 which is a year old now?

#42

by smcleod - opened Sep 8, 2024

Discussion

smcleod

Sep 8, 2024

Neat to see a new Yi Coder model released, well done!

I'm just curious as to why you're comparing it to the old deekseek coder v1 model from around a year ago, rather than current models?

FYI - DeepSeek coder v2 Lite (2.4B active parameters, 16B MoE) replaced it 3 months ago, I can't see why anyone would be using the old v1 model these days.

lorinma

01-ai org Sep 9, 2024

Hi Smcleod,
Thank you for pointing that out. I completely agree that DeepSeek Coder v2 Lite is an impressive model.
The benchmarks we present are not intended as a guide for model selection, but rather as a study of how to achieve better results under comparable controlled conditions, specifically:

Increasing the quality of code data using Iterative Data Filtering, while maintaining a comparable total amount of unique code data (approximately 1T tokens).
with fewer pre-training tokens (3.1T + 2.4T).
with one-third of the # of parameters for dense models.

I hope this explanation clarifies our approach. I will add the comparison results as soon as they become available from our model training team.
Best regards,
Nuo

smcleod

Sep 13, 2024

Thanks for the response! I appreciate that.

smcleod changed discussion status to closed Sep 13, 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