Hugging Face's logo

rawsh
/
mirrorqwen2.5-0.5b-SimPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
cpo
unsloth
text-generation-inference
Inference Endpoints
Model card Files Community
rawsh commited on
Commit
5bb4b0a
·
verified ·
1 Parent(s): 1e76960

Training in progress, step 500

Browse files
Files changed (3) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "q_proj",
24
- "o_proj",
25
  "k_proj",
26
- "v_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
  "q_proj",
 
25
  "k_proj",
26
+ "o_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd1a25c6718ba9d4bbfb03d74d51d3c199779645235b94161331d6cb71add422
3
  size 8676008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a06a4865b46a741f6f137d8c359e21dcbd303395c9831631cd6d97a741058ef
3
  size 8676008
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b62aba6c98c22bc6eab39e0e7691dac4ce0351c20639f4a6e177e35a0bd0c5f7
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21541288a3e0a92183ab1633f9d5f139bab1e093b54f991a05a1ed9a72647084
3
  size 5752