Update README.md

README.md

@@ -4,25 +4,25 @@ tags:
   - text-generation
   - poetry
   - gpt2
-  - rlhf
+  - rl
 license: mit
 datasets:
   - biglam/gutenberg-poetry-corpus
-model_name: GPT2-124 Poetry RLHF
+model_name: GPT2-124 Poetry RL
 library_name: transformers
 ---
 
-# GPT2-124 Fine-Tuned on Poetry with RLHF
+# GPT2-124 Fine-Tuned on Poetry with Reinforcement Learning (RL)
 
 ## Model Description
-This model, **GPT2-124 Poetry RLHF**, is a fine-tuned version of GPT-2 trained on the **Gutenberg Poetry Corpus** with **Reinforcement Learning from Human Feedback (RLHF)**. The model is optimized for poetic generation with enhanced stylistic qualities such as **rhyme, coherence, and creativity**.
+This model, **GPT2-124 Poetry RL**, is a fine-tuned version of GPT-2 trained on the **Gutenberg Poetry Corpus** with **Reinforcement Learning (RL)**. The model is optimized for poetic generation with enhanced stylistic qualities such as **rhyme, coherence, and creativity**.
 
 ## Training Details
 - **Base Model**: [GPT-2 (124M)](https://huggingface.co/gpt2)
 - **Dataset**: [Gutenberg Poetry Corpus](https://huggingface.co/datasets/biglam/gutenberg-poetry-corpus)
 - **Fine-Tuning Approach**:
   - Supervised fine-tuning on poetry lines.
-  - RLHF with custom reward functions:
+  - RL with custom reward functions:
     - **Rhyme Reward**: Encourages rhyming lines.
     - **Coherence Reward**: Ensures logical flow.
     - **Creativity Reward**: Penalizes repetition and rewards unique wording.
@@ -33,8 +33,8 @@ You can generate poetry using the `transformers` library:
 ```python
 from transformers import GPT2LMHeadModel, GPT2Tokenizer
 
-tokenizer = GPT2Tokenizer.from_pretrained("ayazfau/GPT2-124-poetry-RLHF")
-model = GPT2LMHeadModel.from_pretrained("ayazfau/GPT2-124-poetry-RLHF")
+tokenizer = GPT2Tokenizer.from_pretrained("ayazfau/GPT2-124-poetry-RL")
+model = GPT2LMHeadModel.from_pretrained("ayazfau/GPT2-124-poetry-RL")
 
 def generate_poetry(prompt, max_length=50):
     input_ids = tokenizer(prompt, return_tensors="pt").input_ids
@@ -42,7 +42,6 @@ def generate_poetry(prompt, max_length=50):
     return tokenizer.decode(output[0], skip_special_tokens=True)
 
 print(generate_poetry("fear kill dreams,"))
-
 ```
 
 ## Model Performance
@@ -58,4 +57,5 @@ This model is released under the **MIT License**. Feel free to use it for resear
 - Special thanks to the **Gutenberg Poetry Corpus** for providing high-quality literary data.
 
 ---
-_If you use this model, please consider citing it or leaving a star on Hugging Face!_ ⭐
+_If you use this model, please consider citing it or leaving a star on Hugging Face!_ ⭐
+