Update README.md (#13)
Browse files- Update README.md (80f4af7c19f5f8c5ca11872dc6f455a6b8685dba)
Co-authored-by: David Golchinfar <DavidGF@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -36,6 +36,22 @@ New in 2.6
|
|
| 36 |
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
|
| 37 |
You are responsible for any content you create using this model. Enjoy responsibly.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Training
|
| 40 |
It took 2 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
|
| 41 |
|
|
|
|
| 36 |
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
|
| 37 |
You are responsible for any content you create using this model. Enjoy responsibly.
|
| 38 |
|
| 39 |
+
## Evaluation
|
| 40 |
+
|
| 41 |
+
**Open LLM Leaderboard:**
|
| 42 |
+
benchmarked on lm-evaluation-harness v.0.4.1
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
| Metric | Value |
|
| 46 |
+
|-----------------------|---------------------------|
|
| 47 |
+
| Avg. | **61.7** |
|
| 48 |
+
| ARC (25-shot) | 59.81 |
|
| 49 |
+
| HellaSwag (10-shot) | 74.65 |
|
| 50 |
+
| MMLU (5-shot) | 55.38|
|
| 51 |
+
| TruthfulQA (0-shot) | 47.39 |
|
| 52 |
+
| Winogrande (5-shot) | 74.90 |
|
| 53 |
+
| GSM8K (5-shot) | 58.07 |
|
| 54 |
+
|
| 55 |
## Training
|
| 56 |
It took 2 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
|
| 57 |
|