|
--- |
|
language: |
|
- en |
|
library_name: transformers |
|
tags: |
|
- auto-gptq |
|
- AutoRound |
|
license: apache-2.0 |
|
--- |
|
|
|
|
|
## Model Details |
|
|
|
This is [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) quantized with [AutoRound](https://github.com/intel/auto-round/tree/main) (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](https://newsletter.kaitchup.com/p/the-best-quantization-methods-to) |
|
|
|
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): |
|
|
|
 |
|
|
|
|
|
- **Developed by:** [The Kaitchup](https://newsletter.kaitchup.com/) |
|
- **Language(s) (NLP):** English |
|
- **License:** Apache 2.0 license |
