Update README.md

README.md

@@ -6,14 +6,26 @@ library_name: transformers
 pipeline_tag: text-generation
 ---
 
-# Chikuma_10.7B - V2
+# Chikuma_10.7B - V2 (Enhanced with DPO)
 
-This model is the DPO fine tune of [Chikuma_10.7B](https://huggingface.co/sethuiyer/Chikuma_10.7B) using [argilla/distilabel-intel-orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs)
+<p align="center">
+  <img src="https://huggingface.co/sethuiyer/distilabled_Chikuma_10.7B/resolve/main/chikuma_v2.webp" height="256px" alt="Chikuma">
+</p>
 
-# Dataset
+
+This model is the **DPO fine tuned version** of [Chikuma_10.7B](https://huggingface.co/sethuiyer/Chikuma_10.7B), which was a depth upscaled merge of:
+* [sethuiyer/SynthIQ-7b](https://huggingface.co/sethuiyer/SynthIQ-7b)
+* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
+
+The name "Chikuma" is inspired by the [Chikuma River](https://en.wikipedia.org/wiki/Shinano_River), the longest in Japan, known for its continuous flow and meandering path. 
+This metaphorically represents the model's depth, fluidity, and adaptability in processing and understanding language.
+
+
+# Dataset used for Fine Tuning
 Dataset: `/argilla/distilabel-intel-orca-dpo-pairs`
 
 The dataset was roughly ~3000 samples but they were high quality (according to the chosen_score).  
+
 The following filters were applied to the original dataset:
 ```python
 dataset = dataset.filter(
@@ -25,7 +37,7 @@ dataset = dataset.filter(
 ```
 
 # Chat Template
-I decided to go with a slight modification of ChatML.
+The chat template for Chikuma_10.7B - V2 is a modified version of ChatML, optimized for improved interaction and engagement:
 
 ```
 <|im_start|>GPT4 Correct system:
@@ -36,9 +48,10 @@ I decided to go with a slight modification of ChatML.
 {asistant}<|im_end|>
 ```
 
-### Training Hardware
+### Training Environment
+- Hardware: Single A100 80GB GPU in a runpod, utilized for approximately 1.5 hours.
+- Training Script: Accessible via [Google Colab Notebook](https://colab.research.google.com/drive/15iFBr1xWgztXvhrj5I9fBv20c7CFOPBE?usp=sharing). Special thanks to [mlabonne](https://huggingface.co/mlabonne) for providing the template.
 
-I used 1 x A100 80GB in runpod for about 1.5 hours.
 
 ## Usage
 
@@ -83,11 +96,9 @@ print(sequences[0]['generated_text'])
 
 ## Acknowledgements
 
-I'd like to thank the amazing open community and in particular:
+A heartfelt appreciation goes to the vibrant open-source community, particularly:
 
 * The Intel team for publishing a great open dataset and show how well it worked in the first place 
 * Teknium and NousResearch for their awesome work and models.
 * Maxime for sharing such great resources.
-* Argilla for publishing argilla/distilabel-intel-orca-dpo-pairs
-
-
+* Argilla for publishing argilla/distilabel-intel-orca-dpo-pairs