Update README.md
Browse files
README.md
CHANGED
@@ -109,13 +109,13 @@ model-index:
|
|
109 |
---
|
110 |
|
111 |
# SahabatAI-Lion-9B-TIES-v1
|
112 |
-
formerly gemma2-9b-cpt-sahabatai-v1-instruct-BaseTIES (too long :D )
|
113 |
|
114 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642b04e4ecec03b44649e318/rJ0ogty-DbLUEH48Ms5lE.png)
|
115 |
|
116 |
Based on some research, when a finetuned model is merged with its base model with TIES method, there is possibility the merged model will achieve better output.
|
117 |
|
118 |
-
**UPDATE!!! as 20 November 2024, this model is third best model on HF's Open LLM Leaderboard (with Merge/MoErges hide model unchecked) for LLM model below 10B parameters.**
|
119 |
|
120 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642b04e4ecec03b44649e318/8Hv3YtWtzzFlJ0_kUpsT7.png)
|
121 |
|
|
|
109 |
---
|
110 |
|
111 |
# SahabatAI-Lion-9B-TIES-v1
|
112 |
+
formerly gemma2-9b-cpt-sahabatai-v1-instruct-BaseTIES (model name too long :D )
|
113 |
|
114 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642b04e4ecec03b44649e318/rJ0ogty-DbLUEH48Ms5lE.png)
|
115 |
|
116 |
Based on some research, when a finetuned model is merged with its base model with TIES method, there is possibility the merged model will achieve better output.
|
117 |
|
118 |
+
**UPDATE!!! as 20 November 2024, this model is third best model (number one for Gemma2-9B based model) on HF's Open LLM Leaderboard (with Merge/MoErges hide model unchecked) for LLM model below 10B parameters.**
|
119 |
|
120 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642b04e4ecec03b44649e318/8Hv3YtWtzzFlJ0_kUpsT7.png)
|
121 |
|