Upload 9 files

README.md

@@ -44,13 +44,12 @@ ORPO fine tuning was performed for four epoches.
 
 | Epoch | loss | eval_loss |
 | ----- | ---- | --------- |
-| 1 | 10.51274610161781342 | 11.023366928100586 |
-| 2 | 10.09700682163238566 | 10.434176445007324 |
-| 3 | 10.35771694183349566 | 10.179500579833984 |
-| 4 | 10.82988178133964582 | 10.084120750427246 |
+| 1 | 1.20152769684791564 | 1.0501047372817993 |
+| 2 | 1.25755584239959716 | 1.0144596099853516 |
+| 3 | 0.93099724054336543 | 0.9957754611968994 |
+| 4 | 0.88664623498916623 | 0.9857067465782166 |
 
-The fine tuned model is uploaded here to be evaluated by the Open LLM Leaderboard to see if the brain damaged 
-suffered by the non-ORPO model can be healed.
+The fine tuned model is uploaded here to be evaluated by the Open LLM Leaderboard to see if the slightly brain damaged non-ORPO model can be healed. Again, the fine tuning method is also based on one described by [mlabonne](https://towardsdatascience.com/fine-tune-llama-3-with-orpo-56cfab2f9ada) but the input model was read into VRAM by [unsloth](https://github.com/unslothai/unsloth) to allow using the full 40k dataset to run on a single 3090.
 
 ## Benchmark (100.0*raw scores only)
 
@@ -60,10 +59,8 @@ Click on the model name go to the raw score json generated by Open LLM Leaderboa
 | ----- | ------- | ------ | ----|--------- | ---- | ---- | -------- |
 | [gemma-2-2b-jpn-it](https://huggingface.co/datasets/open-llm-leaderboard/results/blob/main/google/gemma-2-2b-jpn-it/results_2024-10-15T15-21-39.173019.json) | 30.82 | 54.11 | 41.43 | 0.0 | 27.52 | 37.17 | 24.67 |
 | gemma-2-2b-jpn-it-abliterated-17-ORPO | TBD | TBD | TBD | TBD | TBD | TBD | TBD |
-| [gemma-2-2b-jpn-it-abliterated-17](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-17/results_2024-10-17T11-26-10.721815.json) | 16.74 | 0.0 | 29.13 | 0.0 | 25.92 | 33.73 | 11.68 |
-| [gemma-2-2b-jpn-it-abliterated-18](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-18/results_2024-10-16T07-58-03.781979.json) | 16.74 | 0.0 | 29.13 | 0.0 | 25.92 | 33.73 | 11.68 |
-
-Indeed, it is quite dumbed down relative to the original. Interestingly, both abliteration models have the same Open LLM results. 
+| [gemma-2-2b-jpn-it-abliterated-17](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-17/results_2024-10-18T15-18-46.821674.json) | 30.29 | 52.65 | 40.46 | 0.0 | 27.18 | 36.90 | 24.55 |
+| [gemma-2-2b-jpn-it-abliterated-18](https://huggingface.co/datasets/open-llm-leaderboard/results/raw/main/ymcki/gemma-2-2b-jpn-it-abliterated-18/results_2024-10-18T15-41-42.399571.json) | 30.61 | 53.02 | 40.96 | 0.0 | 27.35 | 37.30 | 25.05 |
 
 ## How to run this model
 
@@ -103,4 +100,6 @@ huggingface-cli download ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO --include "
 
 ## Credits
 
-Thank you mlabonne for describing his abliteration method.
+Thank you mlabonne for describing his fine tuning method.
+
+Thanks FullOf_Bad_Ideas from LocalLlama for the suggestion of using unsloth to save VRAM.