DPO-7b-beta0.01

README.md

@@ -1,8 +1,16 @@
 ---
+base_model: model/gshf_ours_1_iter_2
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- updated
+- original
 model-index:
 - name: gshf_ours_1_iter_3
   results: []
@@ -13,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gshf_ours_1_iter_3
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [model/gshf_ours_1_iter_2](https://huggingface.co/model/gshf_ours_1_iter_2) on the updated and the original datasets.
 
 ## Model description
 

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }