Instructions to use 01-ai/Yi-34B-Chat-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 01-ai/Yi-34B-Chat-4bits with Transformers:

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

pipe = pipeline("text-generation", model="01-ai/Yi-34B-Chat-4bits")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("01-ai/Yi-34B-Chat-4bits")
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-34B-Chat-4bits")
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 01-ai/Yi-34B-Chat-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "01-ai/Yi-34B-Chat-4bits"
# 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-34B-Chat-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/01-ai/Yi-34B-Chat-4bits

SGLang

How to use 01-ai/Yi-34B-Chat-4bits 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-34B-Chat-4bits" \
    --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-34B-Chat-4bits",
		"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-34B-Chat-4bits" \
        --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-34B-Chat-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 01-ai/Yi-34B-Chat-4bits with Docker Model Runner:
```
docker model run hf.co/01-ai/Yi-34B-Chat-4bits
```

Not working in TGI

by angeligareta - opened Nov 27, 2023

Discussion

angeligareta

Nov 27, 2023

Has someone made this instance work using a HuggingFace Model and deploying it to SageMaker? I am not able to deploy it, any help on which configuration to use would be welcome. I have tried
config = { "HF_MODEL_ID": "01-ai/Yi-34B-Chat-4bits" }
and
config = { "HF_MODEL_ID": "01-ai/Yi-34B-Chat-4bits", 'QUANTIZE': 'awq' }

angeligareta

Nov 28, 2023

This was an error from Sagemaker. A workaround is to generate your own dockerfile with TGI

FROM ghcr.io/huggingface/text-generation-inference:1.1.0

COPY sagemaker-entrypoint.sh entrypoint.sh
RUN chmod +x entrypoint.sh

ENTRYPOINT ["./entrypoint.sh"]

Then build it and upload it to ECR and then input that image_uri to the HuggingFaceModel

huggingface_model = HuggingFaceModel(
    image_uri=custom_image_uri,
    env=hub,
    role=role, 
)

angeligareta changed discussion status to closed Nov 28, 2023

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