Update README.md
Browse files
README.md
CHANGED
|
@@ -108,6 +108,10 @@ model-index:
|
|
| 108 |
name: Open LLM Leaderboard
|
| 109 |
---
|
| 110 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
|
| 112 |
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 113 |
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__RoleBeagle-11B)
|
|
|
|
| 108 |
name: Open LLM Leaderboard
|
| 109 |
---
|
| 110 |
|
| 111 |
+
# RoleBeagle-11B
|
| 112 |
+
|
| 113 |
+
A DPO-finetune from [vicgalle/CarbonBeagle-11B](https://huggingface.co/vicgalle/CarbonBeagle-11B) over a subset of OpenHermesPreferences containting RP conversations.
|
| 114 |
+
It keeps most of the intelligence from CarbonBeagle-11B, and hopefuly can role-play better.
|
| 115 |
|
| 116 |
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 117 |
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__RoleBeagle-11B)
|