Model save

README.md

@@ -0,0 +1,66 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: transformers
+model_name: Qwen2.5-3B-WPO-bf16-1
+tags:
+- generated_from_trainer
+- trl
+- xpo
+licence: license
+---
+
+# Model Card for Qwen2.5-3B-WPO-bf16-1
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+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?"
+generator = pipeline("text-generation", model="MYC081/Qwen2.5-3B-WPO-bf16-1", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with XPO, a method introduced in [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://huggingface.co/papers/2405.21046).
+
+### Framework versions
+
+- TRL: 0.13.0.dev0
+- Transformers: 4.46.2
+- Pytorch: 2.1.2
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+Cite XPO as:
+
+```bibtex
+@article{jung2024binary,
+    title        = {{Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF}},
+    author       = {Tengyang Xie and Dylan J. Foster and Akshay Krishnamurthy and Corby Rosset and Ahmed Awadallah and Alexander Rakhlin},
+    year         = 2024,
+    eprint       = {arXiv:2405.21046}
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	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},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.2"
+}