metadata
language:
- en
library_name: transformers
extra_gated_prompt: >-
This model is exclusively available to Pro subscribers of [The
Kaitchup](https://newsletter.kaitchup.com/). To gain access, subscribe to The
Kaitchup Pro, [subscribe here](https://newsletter.kaitchup.com/subscribe). If
you are already a Pro subscriber, you will find your access token at the
bottom of this
[page](https://newsletter.kaitchup.com/p/introducing-minivoc-faster-and-memory-llms).
datasets:
- HuggingFaceFW/fineweb-edu
Model Details
This is kaitchup/Qwen2.5-7B-Minivoc-32k-v0.1a 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.
The Minivoc approach reduces the vocabulary size to save memory during inference and fine-tuning.
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):
- Developed by: The Kaitchup
- Language(s) (NLP): English
- License: Contact me