Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,26 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
# Better Implementation for [*PairRM*](https://huggingface.co/llm-blender/PairRM)
|
| 5 |
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- openai/summarize_from_feedback
|
| 5 |
+
- openai/webgpt_comparisons
|
| 6 |
+
- berkeley-nest/Nectar
|
| 7 |
+
- Dahoas/instruct-synthetic-prompt-responses
|
| 8 |
+
- Anthropic/hh-rlhf
|
| 9 |
+
- lmsys/chatbot_arena_conversations
|
| 10 |
+
- openbmb/UltraFeedback
|
| 11 |
+
- argilla/ultrafeedback-binarized-preferences-cleaned
|
| 12 |
+
metrics:
|
| 13 |
+
- accuracy
|
| 14 |
+
tags:
|
| 15 |
+
- reward_model
|
| 16 |
+
- reward-model
|
| 17 |
+
- RLHF
|
| 18 |
+
- evaluation
|
| 19 |
+
- llm
|
| 20 |
+
- instruction
|
| 21 |
+
- reranking
|
| 22 |
+
language:
|
| 23 |
+
- en
|
| 24 |
---
|
| 25 |
# Better Implementation for [*PairRM*](https://huggingface.co/llm-blender/PairRM)
|
| 26 |
|