Update README.md
Browse files
README.md
CHANGED
|
@@ -64,3 +64,14 @@ So far not neccisary but may be tuned as needed for suggestions refer to Reasoni
|
|
| 64 |
### Other models
|
| 65 |
This should work well on other UIs the [original model](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview) has usage instructions for them
|
| 66 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
### Other models
|
| 65 |
This should work well on other UIs the [original model](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview) has usage instructions for them
|
| 66 |
|
| 67 |
+
## Benchmark Performance/Without the JavaScript/code_interpreter in GPT4ALL Should easily obtain o1 levals at a reasonable even without GPU Though you may need patience depending on your setup.
|
| 68 |
+
|
| 69 |
+
| Model | AIME24 | AMC23 | GAOKAO2024_I | GAOKAO2024_II | MMLU_STEM | AMPS_Hard | math_comp |
|
| 70 |
+
|---------|--------|-------|--------------|---------------|-----------|-----------|-----------|
|
| 71 |
+
| Qwen2.5-3B-Instruct | 6.67 | 45 | 50 | 35.8 | 59.8 | - | - |
|
| 72 |
+
| SmallThinker | 16.667 | 57.5 | 64.2 | 57.1 | 68.2 | 70 | 46.8 |
|
| 73 |
+
| GPT-4o | 9.3 | - | - | - | 64.2 | 57 | 50 |
|
| 74 |
+
|
| 75 |
+
Example
|
| 76 |
+
|
| 77 |
+
|