Model save
Browse files
README.md
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: google/flan-t5-base
|
| 3 |
library_name: transformers
|
| 4 |
model_name: flan-t5-hh-dpo-lora
|
| 5 |
tags:
|
|
@@ -11,7 +10,7 @@ licence: license
|
|
| 11 |
|
| 12 |
# Model Card for flan-t5-hh-dpo-lora
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
@@ -27,7 +26,7 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jise/huggingface/runs/
|
| 31 |
|
| 32 |
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
| 33 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
model_name: flan-t5-hh-dpo-lora
|
| 4 |
tags:
|
|
|
|
| 10 |
|
| 11 |
# Model Card for flan-t5-hh-dpo-lora
|
| 12 |
|
| 13 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
| 14 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 15 |
|
| 16 |
## Quick start
|
|
|
|
| 26 |
|
| 27 |
## Training procedure
|
| 28 |
|
| 29 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jise/huggingface/runs/f4ep002g)
|
| 30 |
|
| 31 |
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
| 32 |
|