Lewdiculous commited on
Commit
797003d
1 Parent(s): b1ed647

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -34,11 +34,14 @@ Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
34
  ]
35
  ```
36
 
37
- **Submitted card image:**
38
 
39
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/oTFe-bLD1qiOHMeAZMkRr.png)
40
 
41
- ## Original model information:
 
 
 
42
 
43
  # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
44
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__RoleBeagle-11B)
 
34
  ]
35
  ```
36
 
37
+ ## Original model information:
38
 
39
+ # RoleBeagle-11B
40
 
41
+ ![img](https://cdn-uploads.huggingface.co/production/uploads/63df7c44f0c75dfb876272c0/NWE9GsHfROv-1_fLTBpas.png)
42
+
43
+ A DPO-finetune from [vicgalle/CarbonBeagle-11B-truthy](https://huggingface.co/vicgalle/CarbonBeagle-11B-truthy) over a subset of OpenHermesPreferences containting RP conversations.
44
+ It keeps most of the intelligence from CarbonBeagle-11B, and hopefuly can role-play better.
45
 
46
  # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
47
  Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__RoleBeagle-11B)