ISTA-DASLab
/

Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

SpiridonSunRotator commited on May 3

Commit

ffdffd6

•

1 Parent(s): 7bdd700

Update README.md

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -17,4 +17,8 @@ Results:
 | Model      | Quantization | MMLU (5-shot) | GSM8k (8-shot) | ArcC| ArcE| Hellaswag | Winogrande | PiQA | Model size, Gb |
 |------|------|-------|------|------|------|------|------|------|------|
 |meta-llama/Meta-Llama-3-8B-Instruct| None |0.6560 | 0.7475 | 0.5299 | 0.8165 | 0.5771 | 0.7867	| 0.7206 | 16.1 |
-|  | 1x16 | 0.5872 | 0.5087 | 0.4590 | 0.7710 | 0.5491 | 0.7726 | 0.6953 | 4.1 |

 | Model      | Quantization | MMLU (5-shot) | GSM8k (8-shot) | ArcC| ArcE| Hellaswag | Winogrande | PiQA | Model size, Gb |
 |------|------|-------|------|------|------|------|------|------|------|
 |meta-llama/Meta-Llama-3-8B-Instruct| None |0.6560 | 0.7475 | 0.5299 | 0.8165 | 0.5771 | 0.7867	| 0.7206 | 16.1 |
+|  | 1x16 | 0.5872 | 0.5087 | 0.4590 | 0.7710 | 0.5491 | 0.7726 | 0.6953 | 4.1 |
+**UPD** 02.05.2024
+The version of model with improved fine-tuning procedure.