Hugging Face's logo

Weni
/
WeniGPT-2.5.3-Zephyr-7B-zephyr-prompt-LLM_Base_2.0.3_DPO_reduction_variation

Safetensors
Portuguese
trl
DPO
Model card Files Community
Mel-Iza0 commited on
Commit
2ed6581
•
1 Parent(s): e0b54c5

Model save

Browse files
Files changed (4) hide show
  1. README.md +4 -4
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -22,10 +22,10 @@ It achieves the following results on the evaluation set:
22
  - Rewards/rejected: 0.0
23
  - Rewards/accuracies: 0.0
24
  - Rewards/margins: 0.0
25
- - Logps/rejected: -200.4062
26
- - Logps/chosen: -64.1242
27
- - Logits/rejected: -2.0309
28
- - Logits/chosen: -1.6493
29
 
30
  ## Model description
31
 
 
22
  - Rewards/rejected: 0.0
23
  - Rewards/accuracies: 0.0
24
  - Rewards/margins: 0.0
25
+ - Logps/rejected: -204.6461
26
+ - Logps/chosen: -64.2484
27
+ - Logits/rejected: -2.0312
28
+ - Logits/chosen: -1.6494
29
 
30
  ## Model description
31
 
adapter_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "o_proj",
23
  "q_proj",
 
24
  "k_proj",
25
  "v_proj"
26
  ],
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "q_proj",
23
+ "o_proj",
24
  "k_proj",
25
  "v_proj"
26
  ],
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:850c3f2e0e0a28d7713b0947b67d85baa660c4b7a0ae230df4b6a7b3d131d061
3
  size 27297032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a48e27316d8c49fc65841b1d75d4e36e93eeeb1e608536ed7f638c773f7bbc6d
3
  size 27297032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cfbec3cec9a3723bf52c1da5fa438d2709e3e69a485f08f9c2b7e3ee7472df3
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3a881f6315c8118a65817cd1408c52a522c6f80e0749b667ecae967f50cd07
3
  size 5304