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

Libraries

How to use modelscope/Yi-1.5-9B-Chat-AWQ with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/modelscope/Yi-1.5-9B-Chat-AWQ

SGLang

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

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

About Quantization

我们使用modelscope swift仓库进行AWQ 4bit量化. 量化文档可以查看这里. 量化命令如下:

We use the modelscope swift repository to perform AWQ 4bit quantization. Quantization documentation can be found here. The quantization command is as follows:

# Experimental Environment: A100
swift export \
    --quant_bits 4 \
    --model_type yi-1_5-9b-chat \
    --quant_method awq \
    --quant_n_samples 64 \
    --dataset alpaca-zh alpaca-en sharegpt-gpt4-mini \
    --quant_seqlen 4096

Inference:

CUDA_VISIBLE_DEVICES=0 swift infer --model_type yi-1_5-9b-chat-awq-int4

SFT:

CUDA_VISIBLE_DEVICES=0 swift sft --model_type yi-1_5-9b-chat-awq-int4 --dataset leetcode-python-en

Original Model:

YI1.5-9B-Chat

Downloads last month: 3

Safetensors

Model size

9B params

Tensor type

I32

F16