Instructions to use 01-ai/Yi-6B-Chat-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 01-ai/Yi-6B-Chat-4bits with Transformers:

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

pipe = pipeline("text-generation", model="01-ai/Yi-6B-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-6B-Chat-4bits")
model = AutoModelForCausalLM.from_pretrained("01-ai/Yi-6B-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-6B-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-6B-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-6B-Chat-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/01-ai/Yi-6B-Chat-4bits

SGLang

How to use 01-ai/Yi-6B-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-6B-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-6B-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-6B-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-6B-Chat-4bits",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 01-ai/Yi-6B-Chat-4bits with Docker Model Runner:
```
docker model run hf.co/01-ai/Yi-6B-Chat-4bits
```

Error using in transformers with this code

by sudhir2016 - opened Jan 25, 2024

Discussion

sudhir2016

Jan 25, 2024

Code
pipe = pipeline("text-generation", model="01-ai/Yi-6B-Chat-4bits")
Error
ImportError: cannot import name 'MoeModelOutputWithPast' from 'transformers.modeling_outputs' (/usr/local/lib/python3.10/dist-packages/transformers/modeling_outputs.py)

MeisterDeLaV

Jan 30, 2024

Hi there! Could you please provide more details on perhaps your configuration or steps to reproduce this error? Thanks!

sudhir2016

Jan 30, 2024

This code in Google Colab free tier

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="01-ai/Yi-6B-Chat-4bits")

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