Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,15 @@ The GGUF quants for the model are available here - [Llama-3.3-70B-o1-gguf](https
|
|
| 30 |
|
| 31 |
The model was trained using QLoRA fine-tuning. You can find the adapter here - [Llama-3.3-70B-o1-lora](https://huggingface.co/codelion/Llama-3.3-70B-o1-lora).
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
- **Developed by:** codelion
|
| 34 |
- **License:** apache-2.0
|
| 35 |
- **Finetuned from model :** unsloth/llama-3.3-70b-instruct-bnb-4bit
|
|
|
|
| 30 |
|
| 31 |
The model was trained using QLoRA fine-tuning. You can find the adapter here - [Llama-3.3-70B-o1-lora](https://huggingface.co/codelion/Llama-3.3-70B-o1-lora).
|
| 32 |
|
| 33 |
+
## Evaluation results
|
| 34 |
+
|
| 35 |
+
| Model | AIME 2024 pass@1 |
|
| 36 |
+
|-------|------------------|
|
| 37 |
+
| Llama-3.3-70B-o1 | ? |
|
| 38 |
+
| QwQ | 50.0 |
|
| 39 |
+
| Sky-T1-32B-Preview | 43.3|
|
| 40 |
+
| o1-preview | 40.0 |
|
| 41 |
+
|
| 42 |
- **Developed by:** codelion
|
| 43 |
- **License:** apache-2.0
|
| 44 |
- **Finetuned from model :** unsloth/llama-3.3-70b-instruct-bnb-4bit
|