Edit model card

Model Details

This is Qwen/Qwen2.5-7B quantized with AutoRound (asymmetric quantization) and serialized with the GPTQ format in 4-bit. The model has been created, tested, and evaluated by The Kaitchup.

Details on the quantization process and how to use the model here: The Best Quantization Methods to Run Llama 3.1 on Your GPU

It is possible to fine-tune an adapter on top of it following the QLoRA methodology. More about this here: QLoRA with AutoRound: Cheaper and Better LLM Fine-tuning on Your GPU

I used these hyperparameters for quantization:

bits, group_size = 4, 128

autoround = AutoRound(model, tokenizer, nsamples=512, iters=1000, low_gpu_mem_usage=False, bits=bits, group_size=group_size)

autoround.quantize()
output_dir = "./tmp_autoround"
autoround.save_quantized(output_dir, format='auto_gptq', inplace=True) 

Evaluation results (zero-shot evaluation with lm_eval):

arc_challenge, musr, gpqa, mmlu_pro, mmlu….png

  • Developed by: The Kaitchup
  • Language(s) (NLP): English
  • License: Apache 2.0 license
Downloads last month
45
Safetensors
Model size
1.97B params
Tensor type
I32
·
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including kaitchup/Qwen2.5-7B-AutoRound-GPTQ-asym-4bit