Hugging Face's logo

IoakeimE
/
dpo_simplification_model

Transformers
Safetensors
Generated from Trainer
dpo
unsloth
trl
Model card Files
xet
 Community
IoakeimE commited on
Commit
1200d94
·
verified ·
1 Parent(s): 139c2fa

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. README.md +3 -3
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. tokenizer_config.json +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -4,9 +4,9 @@ library_name: transformers
4
  model_name: dpo_simplification_model
5
  tags:
6
  - generated_from_trainer
7
- - dpo
8
- - unsloth
9
  - trl
 
 
10
  licence: license
11
  ---
12
 
@@ -28,7 +28,7 @@ print(output["generated_text"])
28
 
29
  ## Training procedure
30
 
31
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/dpo_smiplification_model/runs/7pyegzvb)
32
 
33
 
34
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
4
  model_name: dpo_simplification_model
5
  tags:
6
  - generated_from_trainer
 
 
7
  - trl
8
+ - unsloth
9
+ - dpo
10
  licence: license
11
  ---
12
 
 
28
 
29
  ## Training procedure
30
 
31
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ioakeime-aristotle-university-of-thessaloniki/dpo_smiplification_model/runs/ix5979rx)
32
 
33
 
34
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
adapter_config.json CHANGED
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
- "o_proj",
37
- "gate_proj",
38
- "k_proj",
39
  "up_proj",
40
  "v_proj",
41
  "q_proj",
42
- "down_proj"
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "down_proj",
 
 
37
  "up_proj",
38
  "v_proj",
39
  "q_proj",
40
+ "k_proj",
41
+ "o_proj",
42
+ "gate_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:190a98a4984e9f5da8b58d8121c95d7a5b7fdbd391605174ab8695e26996c63c
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3bed9d22a0560f48fd07d65df4a6f29da17332a4416ccab2c1303129ccda489
3
  size 167832240
tokenizer_config.json CHANGED
@@ -6179,7 +6179,7 @@
6179
  "legacy": false,
6180
  "model_max_length": 32768,
6181
  "pad_token": "[control_768]",
6182
- "padding_side": "left",
6183
  "sp_model_kwargs": {},
6184
  "spaces_between_special_tokens": false,
6185
  "tokenizer_class": "LlamaTokenizer",
 
6179
  "legacy": false,
6180
  "model_max_length": 32768,
6181
  "pad_token": "[control_768]",
6182
+ "padding_side": "right",
6183
  "sp_model_kwargs": {},
6184
  "spaces_between_special_tokens": false,
6185
  "tokenizer_class": "LlamaTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:194403e6e7cd486ddcf627c7f8c20579b19cf0f5ad3461a5dccdec6a8a807dbb
3
  size 7057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f2812233d6efc36367665f4c3bfce91cda6a152490c79ec80a2e10fd08c183
3
  size 7057