Hugging Face's logo

Quest-AI
/
quest-corruption-14b-grpo-v1.5-s85

Safetensors
qwen2
Model card Files Community
kalomaze commited on
Commit
67bcd93
·
verified ·
1 Parent(s): 605a3c3

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - Quest-AI/quest-corruption-truncated4grpo-2k-dataset-v1
5
+ base_model:
6
+ - Quest-AI/quest-corruption-14b-s110-r3
7
+ ---
8
+
9
+ Alternative version of my prior 14b GRPO attempt with a higher learning rate, on a limited selection of data (2k entries instead of 6k).
10
+
11
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491e00e057b0928b3e07b75/pyrIVlW6jSVRxq803CjWk.png)
12
+
13
+ Wandb with hparams and code in the files section can be found here:
14
+
15
+ [https://wandb.ai/kalomaze/verifiers-examples/runs/mayn2ctv?nw=nwuserkalomaze](https://wandb.ai/kalomaze/verifiers-examples/runs/mayn2ctv?nw=nwuserkalomaze)