Hugging Face's logo

fedric95
/
Meta-Llama-3.1-8B-GGUF

Text Generation
GGUF
PyTorch
facebook
meta
llama
llama-3
Inference Endpoints
Model card Files Community
fedric95 commited on
Commit
4dc0ba8
•
1 Parent(s): 5c399a4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -8
README.md CHANGED
@@ -217,17 +217,16 @@ Original model: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B
217
 
218
  | Benchmark | Quant type | Metric |
219
  | -------- | ---------- | --------- |
220
- | WinoGrande (0-shot) | BF16 | 73.7964 +/- 1.2359 |
221
  | WinoGrande (0-shot) | Q8_0 | 74.1121 +/- 1.2311 |
222
- | WinoGrande (0-shot) | Q6_K | 74.0126 +/- 1.2331 |
223
- | WinoGrande (0-shot) | Q5_K_M | 74.8815 +/- 1.2194 |
224
  | WinoGrande (0-shot) | Q4_K_M | 73.1650 +/- 1.2453 |
225
- | WinoGrande (0-shot) | Q4_K_S | 74.4076 +/- 1.2269 |
226
- | WinoGrande (0-shot) | Q3_K_L | 73.3807 +/- 1.2426 |
227
- | WinoGrande (0-shot) | Q3_K_M | 72.8278 +/- 1.2507 |
228
- | WinoGrande (0-shot) | Q3_K_S | 72.3539 +/- 1.2575 |
229
  | WinoGrande (0-shot) | Q2_K | 68.4294 +/- 1.3063 |
230
-
 
 
 
 
231
 
232
  ## Downloading using huggingface-cli
233
 
 
217
 
218
  | Benchmark | Quant type | Metric |
219
  | -------- | ---------- | --------- |
 
220
  | WinoGrande (0-shot) | Q8_0 | 74.1121 +/- 1.2311 |
 
 
221
  | WinoGrande (0-shot) | Q4_K_M | 73.1650 +/- 1.2453 |
222
+ | WinoGrande (0-shot) | Q3_K_M | 72.7703 +/- 1.2511 |
223
+ | WinoGrande (0-shot) | Q3_K_S | 72.3757 +/- 1.2567 |
 
 
224
  | WinoGrande (0-shot) | Q2_K | 68.4294 +/- 1.3063 |
225
+ | HellaSwag (0-shot) | Q8_0 | 79.41645091 |
226
+ | HellaSwag (0-shot) | Q4_K_M | 79.05795658 |
227
+ | HellaSwag (0-shot) | Q3_K_M | 79.41645091 |
228
+ | HellaSwag (0-shot) | Q3_K_S | 76.93686517 |
229
+ | HellaSwag (0-shot) | Q2_K | 72.16689902 |
230
 
231
  ## Downloading using huggingface-cli
232