neph1 commited on
Commit
8cce276
·
verified ·
1 Parent(s): 55f3cea

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -9,6 +9,8 @@ language:
9
 
10
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/pLcriXAfp3Y9Z0RGwwVUB.png)
11
 
 
 
12
  Updated 240413: Dataset: 14002 rows. Rank: 64/128. Increased diversity of the instruct dataset. 4k context length training
13
  A light DPO pass to 'align' the model and make it less prone to saying untrue things. Ref: https://huggingface.co/datasets/neph1/truthy-dpo-v0.1-swe
14
 
 
9
 
10
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/pLcriXAfp3Y9Z0RGwwVUB.png)
11
 
12
+ Update 250114: There is now a new bellman with mistral-7b-instruct-v3: https://huggingface.co/neph1/bellman-mistral-7b-instruct-v0.3
13
+
14
  Updated 240413: Dataset: 14002 rows. Rank: 64/128. Increased diversity of the instruct dataset. 4k context length training
15
  A light DPO pass to 'align' the model and make it less prone to saying untrue things. Ref: https://huggingface.co/datasets/neph1/truthy-dpo-v0.1-swe
16