Hugging Face's logo

WindowsXp-Beta
/
RAPO

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
WindowsXp-Beta commited on
Commit
191ccb3
·
verified ·
1 Parent(s): 315a9b4

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/config.json +1 -1
  2. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/final_checkpoint/config.json +1 -1
  3. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/final_checkpoint/model.safetensors +1 -1
  4. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/model-00001-of-00004.safetensors +1 -1
  5. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/model-00002-of-00004.safetensors +1 -1
  6. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/model-00003-of-00004.safetensors +1 -1
  7. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/model-00004-of-00004.safetensors +1 -1
  8. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_1/training_args.bin +1 -1
qwen2.5_7B_cpo_mappo_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_MaPPO_beta_0_001_alpha_0_1/rapo_CPO_MaPPO_beta_0_001_alpha_0_1_CPO_MaPPO_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_mappo_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_MaPPO_beta_0_001_alpha_0_1/rapo_CPO_MaPPO_beta_0_001_alpha_0_1_CPO_MaPPO_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_mappo_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:edbcdc37fca9b21dfcbbe3040219aac6c212fcc3041e112383428f08f88b8fa2
3
  size 701024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ba0c85e3682df70ae6802475acf50f24058f53ee1670489d984ed61be26d58
3
  size 701024
qwen2.5_7B_cpo_mappo_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:ba5c0a559b7ddbf2a5dbfa023559339913505cc0a97baf0982cd9912787825d8
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230ecf180f67cb8c09d2b4552c79c9c5b81265a89d300df2c99c7fbff61cd743
3
  size 4877660776
qwen2.5_7B_cpo_mappo_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 sha256:564abbbe791977000251c46e6097e2a59fdf1eddb27617e994a981331b702ae7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166e13a38f049378880c2324488dc599b70470df3f5de483769825e46cee25b2
3
  size 4932751008
qwen2.5_7B_cpo_mappo_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 sha256:5dbd55b3ae2ac694390535f21417cbf4cc25e8db60baa506c1992c671f8ed8e7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e09c55f58db6cc78bc2e8744c2802197e5d160165c0c0b160472c7295d0665
3
  size 4330865200
qwen2.5_7B_cpo_mappo_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 sha256:9dad66d2accbbfcf8cc678e70279d6fd78cb22d8c602cf27c80451a690b587fd
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6b26c133c1d85e6064362634a94c040e5e6f7f80d160cd29c207f62c1475ac
3
  size 1089994880
qwen2.5_7B_cpo_mappo_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:a2be410550e24cd957c944c615856884dcebece3a281ffc7b69f534e77b817c3
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cbe0c1c49e838190821aa414813af2860eee733e7eb12045ed80808dc37f31d
3
  size 7480