Instructions to use Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit with Transformers:

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

pipe = pipeline("text-generation", model="Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit")
model = AutoModelForCausalLM.from_pretrained("Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit

SGLang

How to use Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit 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 "Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit with Docker Model Runner:
```
docker model run hf.co/Yhyu13/Xwin-Math-7B-V1.0-QUIP-2bit
```

Edit

PS : https://github.com/Cornell-RelaxML/quip-sharp/issues/13

As mentioned in the above issue thread,

for accurate hessian generation, use a larger devset (e.g., 4096) and consider accumulating hessians in fp32 if consumer GPUs with fast fp64 are not available.
changing the Hessian dataset from a natural language dataset to a mathematical dataset, as the task is a math model.

Experiment QUIP 2-bit E8P12 version that works in textgen-webui with quip mode loader

Generated by using scripts from https://gitee.com/yhyu13/llama_-tools

Original weight : https://huggingface.co/Xwin-LM/Xwin-Math-7B-V1.0

GPTQ 4bit : https://huggingface.co/Yhyu13/Xwin-Math-7B-V1.0-GPTQ-4bit

This repo used hessian_offline_llama.py provided by QUIP repo to generate hessian specifically for the orignal model before applying Quip quantization.

It took quite a long time for hessian for all 31 layers, about 6 hours for 7B models on a single RTX3090. I am not sure if I made any error.

QUIP byproducts are also uploaded.

Perplexity calcaultead using eval_ppl.py provided by QUIP repo QUIP PPL:

wikitext2 perplexity: 11.247852325439453
c4 perplexity: 16.275997161865234

Original model PPL:

wikitext2 perplexity: 6.042122840881348
c4 perplexity: 8.430611610412598

Looks like something is wrong, the quantized model is a disaster.

Here is some testing done in textgen-webui, I was using Q&A from this dataset https://huggingface.co/datasets/TIGER-Lab/MathInstruct

It seems the 2 bit could hardly answer any question correctly, in compare to GPTQ 4bit version. But the https://huggingface.co/relaxml/Llama-2-13b-E8P-2Bit model made by the author of QUIP seems to work fine, just as good as GPTQ.

So in conclusion, this is a very experimental model that I made just to testify QUIP, I may made some error. But I think it is a good start.

QUIP 2 bit version: $Alt text$

GPTQ 4 bit version: $Alt text$

Downloads last month: 4

Safetensors

Model size

1B params

Tensor type

F16

I16