Dongfu Jiang
commited on
Commit
•
a20b0a8
1
Parent(s):
9ea925c
Update README.md
Browse files
README.md
CHANGED
|
@@ -197,6 +197,16 @@ We test the pairwise comparison on
|
|
| 197 |
- [HHH-alignment](https://huggingface.co/datasets/HuggingFaceH4/hhh_alignment)
|
| 198 |
- [MT-bench-human-judgements](https://huggingface.co/datasets/lmsys/mt_bench_human_judgments)
|
| 199 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
#### Auto-J Pairwise test data performance
|
| 201 |
|
| 202 |
| Model | Summ | Exam | Code | Rewriting | Crea W | Func W | Comm | NLP | Overall |
|
|
|
|
| 197 |
- [HHH-alignment](https://huggingface.co/datasets/HuggingFaceH4/hhh_alignment)
|
| 198 |
- [MT-bench-human-judgements](https://huggingface.co/datasets/lmsys/mt_bench_human_judgments)
|
| 199 |
|
| 200 |
+
|
| 201 |
+
### Training Datasets
|
| 202 |
+
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback)
|
| 203 |
+
- [openai/webgpt_comparisons](https://huggingface.co/datasets/openai/webgpt_comparisons)
|
| 204 |
+
- [Dahoas/instruct-synthetic-prompt-responses](https://huggingface.co/datasets/Dahoas/instruct-synthetic-prompt-responses)
|
| 205 |
+
- [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf)
|
| 206 |
+
- [lmsys/chatbot_arena_conversations](https://huggingface.co/datasets/lmsys/chatbot_arena_conversations)
|
| 207 |
+
- [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback)
|
| 208 |
+
|
| 209 |
+
|
| 210 |
#### Auto-J Pairwise test data performance
|
| 211 |
|
| 212 |
| Model | Summ | Exam | Code | Rewriting | Crea W | Func W | Comm | NLP | Overall |
|