This is OpenLLaMA 3B V2 finetuned on EverythingLM Data(ShareGPT format more cleaned) for 1 epochs.
Prompt template:
### HUMAN:
{prompt}
### RESPONSE:
<leave a newline for the model to answer>
GGML quants available here.
GPTQ quants available here.
Note: Don't expect this model to be good, I was just starting out to finetune. So don't roast me please!
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 41.71 |
| ARC (25-shot) | 43.17 |
| HellaSwag (10-shot) | 72.68 |
| MMLU (5-shot) | 28.46 |
| TruthfulQA (0-shot) | 39.09 |
| Winogrande (5-shot) | 65.59 |
| GSM8K (5-shot) | 1.29 |
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 41.71 |
| AI2 Reasoning Challenge (25-Shot) | 43.17 |
| HellaSwag (10-Shot) | 72.68 |
| MMLU (5-Shot) | 28.46 |
| TruthfulQA (0-shot) | 39.09 |
| Winogrande (5-shot) | 65.59 |
| GSM8k (5-shot) | 1.29 |
- Downloads last month
- 1,048
Model tree for acrastt/Marx-3B
Dataset used to train acrastt/Marx-3B
Spaces using acrastt/Marx-3B 29
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard43.170
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard72.680
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard28.460
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard39.090
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard65.590
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard1.290