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

Libraries

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

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

pipe = pipeline("text-generation", model="01-ai/Yi-Coder-1.5B-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-1.5B-Chat")
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-Coder-1.5B-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-1.5B-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-1.5B-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-1.5B-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Corrected eos token

by CISCai - opened Sep 4, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-2

CISCai

Sep 4, 2024

According to tokenizer_config.json the eos token should be <|im_end|>, and according to my own testing this is correct, using the wrong token results in infinite generation responses.

Corrected eos tokena4099b64

haijian06

Sep 5, 2024

Hi 👋 @CISCai Hello, could I see how you are specifically using it (such as the inference code)? This would help us accurately reproduce your issue. Thank you very much! 🙏

CISCai

Sep 5, 2024

GGUFs get broken by this, compare my GGUFs to all others, I'm guessing transformers override the value from special_tokens_map.json and thus function correctly, however llama.cpps conversion script gets it from config.json.

haijian06

Sep 5, 2024

Thank you very much for your reply, we had an update to the tokenizer_config.json file about 6 hours ago, are you still having problems with the model?

CISCai

Sep 5, 2024

•

edited Sep 5, 2024

Yes, that only addressed the tokenization of <|im_start|>, which was a different issue.

If you use Huggingface's GGUF viewer you can see that all other GGUFs have tokenizer.ggml.eos_token_id set to 2, instead of 7, which is the correct value.

CISCai

Sep 5, 2024

BTW, in case some of the other GGUFs never get updated and someone stumbles upon this PR later, you can use my GGUF Editor to easily set the correct token and download an updated version of the GGUF. :)

haijian06

Sep 5, 2024

Hi @CISCai , thank you very much for your contribution! I've fixed the issue. Thank you again so much! 🙏

haijian06 changed pull request status to merged Sep 5, 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