DPO-7b-beta0.01
Browse files
README.md
CHANGED
|
@@ -2,10 +2,14 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- trl
|
| 6 |
- dpo
|
| 7 |
-
- generated_from_trainer
|
| 8 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
|
|
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: nash_dpo_doff_no_golden_iter_1
|
| 11 |
results: []
|
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# nash_dpo_doff_no_golden_iter_1
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Logits/chosen: -2.7444
|
| 22 |
- Logits/rejected: -2.6646
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
+
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- dpo
|
|
|
|
| 9 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
| 10 |
+
datasets:
|
| 11 |
+
- updated
|
| 12 |
+
- original
|
| 13 |
model-index:
|
| 14 |
- name: nash_dpo_doff_no_golden_iter_1
|
| 15 |
results: []
|
|
|
|
| 20 |
|
| 21 |
# nash_dpo_doff_no_golden_iter_1
|
| 22 |
|
| 23 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the updated and the original datasets.
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Logits/chosen: -2.7444
|
| 26 |
- Logits/rejected: -2.6646
|