Hugging Face's logo

WindowsXp-Beta
/
RAPO

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
WindowsXp-Beta commited on
Commit
ea44a70
·
verified ·
1 Parent(s): d6ef424

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/config.json +1 -1
  2. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/final_checkpoint/config.json +1 -1
  3. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/final_checkpoint/model.safetensors +1 -1
  4. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00001-of-00004.safetensors +1 -1
  5. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00002-of-00004.safetensors +1 -1
  6. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00003-of-00004.safetensors +1 -1
  7. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00004-of-00004.safetensors +1 -1
  8. qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/training_args.bin +1 -1
qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/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_2/rapo_CPO_MaPPO_beta_0_001_alpha_0_2_CPO_MaPPO_beta_0_001_alpha_0_2_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_2/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_2/rapo_CPO_MaPPO_beta_0_001_alpha_0_2_CPO_MaPPO_beta_0_001_alpha_0_2_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_2/final_checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58cfa8dee846dd0cd4ca17279e3c84b81abcd10d85b3be34cd106f6fe9cf8faa
3
  size 701024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547ca190a8bcb5c4af91fa9fc66795334bae90d3433f0db9f50ff55506f47c69
3
  size 701024
qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b669d2b8122d52fc60b9761edae9de8fd1cde8e12a51dedf2a2737fca2ac6025
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69a632200311046cdd4160bdb4643d2f0904978f3d7f18659b7b5271c8d7e74
3
  size 4877660776
qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cac916d96fec10ab51d4a4eeed5165279f884915f8bf20c20530b45443e2086c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a3e7a09c96f767c12ad72e707510a50310efa6e6e628d42baf167f7c10e431
3
  size 4932751008
qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7070137fb165ebd90b9fa06cf4105af7b53ab43992225bdd1515701b073350a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b466739c4fb687dbf12d7ef79b9acdfb550eabd8afd42b3a75c7f1319cc1dcf5
3
  size 4330865200
qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7c18e4a452d2150974c213a762c4a2acf49fd010c1add8a6980141e24bc9f2f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013209ffdca10a5c08b8189c29a50c63f06666ed7cc7f70974b2e6d35a3095ed
3
  size 1089994880
qwen2.5_7B_cpo_mappo_beta_0_001_alpha_0_2/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f73d873a15df87e8b0962a34a2cb45eeaa6cf47dd16bb6401e3a0eca6401c0
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3801c9fc92ddfb6df8e4e16461e3d362be321378f579714004385b6df51c8924
3
  size 7480