Update README.md
Browse files
README.md
CHANGED
|
@@ -34,11 +34,18 @@ datasets:
|
|
| 34 |
|
| 35 |
Some GGUF quantizations are included as well.
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
Open_Orca_Llama-3-8B-unsloth.Q8_0.gguf:
|
| 38 |
- **MMLU-Test:** Final result: 39.3818 +/- 0.4138
|
|
|
|
| 39 |
|
| 40 |
Meta-Llama-3-8B.Q8_0.gguf:
|
| 41 |
-
- **MMLU-Test:**
|
|
|
|
| 42 |
|
| 43 |
Llama.cpp Options For Testing:
|
| 44 |
--samplers "tfs;typical;temp" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12
|
|
|
|
| 34 |
|
| 35 |
Some GGUF quantizations are included as well.
|
| 36 |
|
| 37 |
+
|
| 38 |
+
llama-3-8b-bnb-4bit.Q8_0.gguf:
|
| 39 |
+
- **MMLU-Test:** Pending..
|
| 40 |
+
- **Arc-Easy:** Pending..
|
| 41 |
+
|
| 42 |
Open_Orca_Llama-3-8B-unsloth.Q8_0.gguf:
|
| 43 |
- **MMLU-Test:** Final result: 39.3818 +/- 0.4138
|
| 44 |
+
- **Arc-Easy:** Final result: 67.3684 +/- 1.9656
|
| 45 |
|
| 46 |
Meta-Llama-3-8B.Q8_0.gguf:
|
| 47 |
+
- **MMLU-Test:** Final result: 40.8664 +/- 0.4163
|
| 48 |
+
- **Arc-Easy:** Final result: 74.3860 +/- 1.8299
|
| 49 |
|
| 50 |
Llama.cpp Options For Testing:
|
| 51 |
--samplers "tfs;typical;temp" --draft 32 --ctx-size 8192 --temp 0.82 --tfs 0.8 --typical 1.1 --repeat-last-n 512 --batch-size 8192 --repeat-penalty 1.0 --n-gpu-layers 100 --threads 12
|