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
aa6de07
·
verified ·
1 Parent(s): bc975e5

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. adapter_config.json +3 -3
  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
- - trl
8
- - unsloth
9
  - dpo
 
 
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/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).
@@ -37,9 +37,9 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
37
 
38
  - TRL: 0.24.0
39
  - Transformers: 4.57.3
40
- - Pytorch: 2.9.0
41
  - Datasets: 4.3.0
42
- - Tokenizers: 0.22.1
43
 
44
  ## Citations
45
 
 
4
  model_name: dpo_simplification_model
5
  tags:
6
  - generated_from_trainer
 
 
7
  - dpo
8
+ - unsloth
9
+ - trl
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/runs/2qlb2fat)
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).
 
37
 
38
  - TRL: 0.24.0
39
  - Transformers: 4.57.3
40
+ - Pytorch: 2.10.0
41
  - Datasets: 4.3.0
42
+ - Tokenizers: 0.22.2
43
 
44
  ## Citations
45
 
adapter_config.json CHANGED
@@ -34,12 +34,12 @@
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",
 
34
  "revision": null,
35
  "target_modules": [
36
  "down_proj",
37
+ "gate_proj",
38
  "v_proj",
39
  "q_proj",
 
40
  "o_proj",
41
+ "k_proj",
42
+ "up_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:d03c1a01d0ca597808c0cbd6d52c1b0601b5ef20e59e2e15ae017803184bb20d
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6d94fda51931b0ba8c8a4754d02ce85730747c7c3118be74846b6c995436b5
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 sha256:53f2812233d6efc36367665f4c3bfce91cda6a152490c79ec80a2e10fd08c183
3
  size 7057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e909576e7d07255b502584806f6b4a1943f5ced7870d8bb3b95e82f142ae957a
3
  size 7057