jeromeramos commited on
Commit
1e53920
·
verified ·
1 Parent(s): 30f1cb9

Model save

Browse files
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: inter-play-sim-assistant-dpo-test
4
+ tags:
5
+ - generated_from_trainer
6
+ - trl
7
+ - dpo
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for inter-play-sim-assistant-dpo-test
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
22
+ generator = pipeline("text-generation", model="Sim4Rec/inter-play-sim-assistant-dpo-test", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+ [<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/jerome-ramos-20/huggingface/runs/rs70k5bm)
30
+
31
+
32
+ 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).
33
+
34
+ ### Framework versions
35
+
36
+ - TRL: 0.14.0
37
+ - Transformers: 4.51.3
38
+ - Pytorch: 2.6.0
39
+ - Datasets: 3.0.1
40
+ - Tokenizers: 0.21.0
41
+
42
+ ## Citations
43
+
44
+ Cite DPO as:
45
+
46
+ ```bibtex
47
+ @inproceedings{rafailov2023direct,
48
+ title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
49
+ author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
50
+ year = 2023,
51
+ booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
52
+ url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
53
+ editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
54
+ }
55
+ ```
56
+
57
+ Cite TRL as:
58
+
59
+ ```bibtex
60
+ @misc{vonwerra2022trl,
61
+ title = {{TRL: Transformer Reinforcement Learning}},
62
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
63
+ year = 2020,
64
+ journal = {GitHub repository},
65
+ publisher = {GitHub},
66
+ howpublished = {\url{https://github.com/huggingface/trl}}
67
+ }
68
+ ```
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997327870312639,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.2128710214231835,
5
+ "train_runtime": 9706.3948,
6
+ "train_samples": 44906,
7
+ "train_samples_per_second": 4.626,
8
+ "train_steps_per_second": 0.145
9
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.51.3"
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997327870312639,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.2128710214231835,
5
+ "train_runtime": 9706.3948,
6
+ "train_samples": 44906,
7
+ "train_samples_per_second": 4.626,
8
+ "train_steps_per_second": 0.145
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff