Hugging Face's logo

hZzy
/
qwen2.5-0.5b-expo-DPO-ES-0.01

Safetensors
qwen2
alignment-handbook
ndcg
trl
expo
Generated from Trainer
Model card Files Community
hZzy commited on
Commit
2efc2e6
·
verified ·
1 Parent(s): b1acf0c

Training in progress, step 350

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.42.0",
26
- "use_cache": true,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 151665
 
23
  "tie_word_embeddings": true,
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.42.0",
26
+ "use_cache": false,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 151665
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6fbadd5f72d783e4eef10b0ec932f1d5e13f20e83ebacd844cdbf5fb249cb55
3
  size 1975192208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f539545b018976dbce6dc0923e193b8fdb77c11b5c5c100b4f2183deb0db46
3
  size 1975192208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76d8a7511dedab9d1ca256976300f01baf9b6d26c68e55cf5265b8513018332d
3
  size 8120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ef546fe9cc67b43ade22bdb58191962b2102c5578d9dc4c0f9983e22a36d23
3
  size 8120