Downloads · 30 days
79
14% of all-time downloads
Qwen2.5-7B-Instruct-AutoRound-GPTQ-asym-4bit
kaitchup/Qwen2.5-7B-Instruct-AutoRound-GPTQ-asym-4bit
Qwen2.5-7B-Instruct-AutoRound-GPTQ-asym-4bit is a text generation model from kaitchup. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is Qwen/Qwen2.5-7B-Instruct 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.
All-time downloads
575
Public
Parameters
7.6B
5.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.6 GB · 100%
Parameter types
How the weights are stored.
I326.5B · 86%
Try a prompt
Model card
From the Hugging Face model README
Model Details
This is Qwen/Qwen2.5-7B-Instruct 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
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
- Language(s) (NLP): English
- License: Apache 2.0 license
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Oct 12, 2024
- Updated
- Oct 18, 2024