Junxiong Wang
commited on
Commit
·
8b2d401
1
Parent(s):
fed113d
add models
Browse files
README.md
CHANGED
|
@@ -1,21 +1,23 @@
|
|
| 1 |
---
|
| 2 |
base_model: JunxiongWang/mamba_0_5_sft
|
| 3 |
tags:
|
|
|
|
| 4 |
- alignment-handbook
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- HuggingFaceH4/ultrafeedback_binarized
|
| 8 |
model-index:
|
| 9 |
- name: mamba_0_5_dpo_ep3
|
| 10 |
-
results: []
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
# mamba_0_5_dpo_ep3
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [JunxiongWang/
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.7141
|
| 21 |
- Rewards/chosen: -5.3346
|
|
|
|
| 1 |
---
|
| 2 |
base_model: JunxiongWang/mamba_0_5_sft
|
| 3 |
tags:
|
| 4 |
+
- mamba
|
| 5 |
- alignment-handbook
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- HuggingFaceH4/ultrafeedback_binarized
|
| 9 |
model-index:
|
| 10 |
- name: mamba_0_5_dpo_ep3
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
+
Please check [here](https://github.com/jxiw/MambaInLlama/tree/main) for details.
|
| 14 |
+
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
# mamba_0_5_dpo_ep3
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [JunxiongWang/mamba_0_5_dpo_ep3](https://huggingface.co/JunxiongWang/mamba_0_5_sft) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
- Loss: 0.7141
|
| 23 |
- Rewards/chosen: -5.3346
|