Hugging Face's logo

WindowsXp-Beta
/
RAPO

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
WindowsXp-Beta commited on
Commit
9506f67
·
verified ·
1 Parent(s): ea44a70

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/config.json +1 -1
  2. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/final_checkpoint/config.json +1 -1
  3. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/final_checkpoint/model.safetensors +1 -1
  4. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/model-00001-of-00004.safetensors +1 -1
  5. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/model-00002-of-00004.safetensors +1 -1
  6. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/model-00003-of-00004.safetensors +1 -1
  7. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/model-00004-of-00004.safetensors +1 -1
  8. qwen2.5_7B_cpo_beta_0_001_alpha_0_2/training_args.bin +1 -1
qwen2.5_7B_cpo_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_beta_0_001_alpha_0_2/rapo_CPO_beta_0_001_alpha_0_2_CPO_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_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_beta_0_001_alpha_0_2/rapo_CPO_beta_0_001_alpha_0_2_CPO_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_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 sha256:6ae13e212623fc05476ae74c48d939c38337c644fd0f0fb7404a7b657979f266
3
  size 701024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4583a20a91012c7533178f42f8897bdc41d377c7827acdc73f24487847adcc67
3
  size 701024
qwen2.5_7B_cpo_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 sha256:993f42884a1786026f40be67b0e5747c3d2487d6f4636612bfa31a51cf92856f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:508b7fae7e7b707c54f52a165515bcac879954b11eb045e99ab2cd41530ade18
3
  size 4877660776
qwen2.5_7B_cpo_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:f68905ca438cf718f3bca2543eadaf0b1ff11e734fecafcddb1d84f7304974c4
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13f4d95d45c97e15491c5c0bd89078ada14fc9d1bbf431091b30ea9132dfc9c
3
  size 4932751008
qwen2.5_7B_cpo_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 sha256:78d2594676b8a1461ff39bddaf4ae4fc30ffb774b5857102debe328049aaad49
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14f5496ba18e4899031b4ef881ec1f5a3a8f20776ffd3ca53f7f308900364aa
3
  size 4330865200
qwen2.5_7B_cpo_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 sha256:0c29dc3e5e0571a141e1ba89ccfa2b3b45c2a73af0e393399422e43bde39f85c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92053832bbe286205cec14ab6cd853b9aa9965b5c287a852cd04134e67bc93de
3
  size 1089994880
qwen2.5_7B_cpo_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 sha256:3e015f31fe543e8aa7d3ffd37c8f34ef76c6d6831d01e83a2ffbcf5daec994cc
3
  size 7480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1eb23e8ee9d0f86e4bf48f9f007c2110281ead044826938bdb4be9c3c4b6e3
3
  size 7480