Upload DPO LLM Judge fine-tuned model

README.md

@@ -1,51 +1,73 @@
 ---
-license: apache-2.0
 base_model: meta-llama/Llama-3.2-1B-Instruct
+library_name: peft
+model_name: dpo_llm_judge_model
 tags:
+- base_model:adapter:meta-llama/Llama-3.2-1B-Instruct
 - dpo
-- peft
-- llama
-- preference-learning
-model-index:
-- name: llama3-dpo-llm judge
-  results: []
+- lora
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
 ---
 
-# Llama-3.2-1B DPO LLM Judge
+# Model Card for dpo_llm_judge_model
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) using Direct Preference Optimization (DPO).
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Model Details
+## Quick start
 
-- **Base Model**: meta-llama/Llama-3.2-1B-Instruct
-- **Training Method**: Direct Preference Optimization (DPO)
-- **Preference Source**: LLM Judge
-- **LoRA Configuration**:
-  - r: 8
-  - alpha: 16
-  - target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj']
-- **Training Steps**: 250
-- **Learning Rate**: 0.0002
+```python
+from transformers import pipeline
 
-## Usage
+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="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
+## Training procedure
 
-base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
-model = PeftModel.from_pretrained(base_model, "pyamy/llama3-dpo-llm judge")
+ 
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
-```
 
-## Training Details
+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).
 
-- Dataset: 50 instructions from LIMA
-- Responses per instruction: 5
-- Preference judgment: LLM Judge
-- Training framework: TRL DPOTrainer
+### Framework versions
 
-## Performance
+- PEFT 0.17.0
+- TRL: 0.21.0
+- Transformers: 4.55.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 4.0.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    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},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
 
-See evaluation results in the repository for detailed performance metrics.
+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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```