AQLM+PV
Collection
Official AQLM quantizations for "PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression": https://arxiv.org/abs/2405.14852
•
20 items
•
Updated
•
13
Official AQLM quantization of meta-llama/Meta-Llama-3.1-8B-Instruct finetuned with PV-Tuning.
For this quantization, we used 1 codebook of 16 bits and groupsize of 8.
Results:
Model | Quantization | MMLU (5-shot) | ArcC | ArcE | Hellaswag | PiQA | Winogrande | Model size, Gb |
---|---|---|---|---|---|---|---|---|
meta-llama/Meta-Llama-3.1-8B-Instruct | None | 0.6817 | 0.5162 | 0.8186 | 0.5909 | 0.8014 | 0.7364 | 16.1 |
1x16g8 | 0.5966 | 0.4667 | 0.7790 | 0.5582 | 0.7878 | 0.7001 | 4.1 |
Note
We used lm-eval=0.4.0
for evaluation.
UPD (09.08.2024)
Uploaded new version finetuned on more data for longer with better quality.