Hugging Face's logo

WindowsXp-Beta
/
RAPO

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
WindowsXp-Beta commited on
Commit
d6ef424
·
verified ·
1 Parent(s): 191ccb3

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/config.json +1 -1
  2. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/final_checkpoint/config.json +1 -1
  3. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/final_checkpoint/model.safetensors +1 -1
  4. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00001-of-00004.safetensors +1 -1
  5. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00002-of-00004.safetensors +1 -1
  6. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00003-of-00004.safetensors +1 -1
  7. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00004-of-00004.safetensors +1 -1
  8. qwen2.5_7B_cpo_beta_0_001_alpha_0_1/training_args.bin +1 -1
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Online-RLHF/checkpoint/qwen2.5-7B/rapo_CPO_beta_0_001_alpha_0_1/rapo_CPO_beta_0_001_alpha_0_1_CPO_beta_0_001_alpha_0_1_iter2",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "Online-RLHF/sft_checkpoint/Qwen2.5-7B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/final_checkpoint/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Online-RLHF/checkpoint/qwen2.5-7B/rapo_CPO_beta_0_001_alpha_0_1/rapo_CPO_beta_0_001_alpha_0_1_CPO_beta_0_001_alpha_0_1_iter2",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "Online-RLHF/sft_checkpoint/Qwen2.5-7B-Instruct",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/final_checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c55ba723d6daee8f8b572569b337f01b88b8dd3f3bb89b62f57eadb450d5e5d
3
  size 701024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5db9ff789bced0931f1c233252c41d273b81226696e5e16a48702ff4d2d630c
3
  size 701024
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbca931abe4b2279d492b2c880a68969a573ebefe651091d43949ec4ee997f1d
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:226bd328eda44083e8db50efc79e26cef6f11767141ebc8ee112a8617d36eb35
3
  size 4877660776
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180367bd50c99f54a0acfa5e8e0aeb034c9effd6c6fba82a3e49a322d44f23b7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b733789a24dd50b12b300217d5531ba2a353c6f8195cdd8c15c11607b4538636
3
  size 4932751008
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac30390f348f6d6d8bbafcd2decff5a997c963087836c9904c89f42ab0cff18
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd085053c466d5578436f51b68974df45744152d1e174ab8bfed3a75f9cfd29
3
  size 4330865200
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b93551d6a549e9167ec482b79dbf26305cf6930b9dba928233b9de770683c64b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f862122dcf4498413dbe7e139491e1ac624f7542fd40a47c4c57b39b21ce1e
3
  size 1089994880
qwen2.5_7B_cpo_beta_0_001_alpha_0_1/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33f2f75b9da164e48221096583bb7ef2f1f6c6ee8475d2d4119652ca10ad24d0
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7c66026cd9ac043e42a984f0209d6773c66c1e3155633533b4689909b28327
3
  size 7480