Update README.md

README.md

@@ -8,14 +8,22 @@ base_model: meta-llama/Meta-Llama-3-8B
 
 ## Overview
 
-**nephra v1.0** is a model built for roleplaying sessions, trained on roleplay and instruction-style datasets.
+**nephra v1** is primarily a model built for roleplaying sessions, trained on roleplay and instruction-style datasets.
+
+## Model Details
+- **Developed by**: [Sao10K](https://huggingface.co/Sao10K)
+- **Model type**: Text-based Large Language Model
+- **License**: [Meta Llama 3 Community License Agreement](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE)
+- **Finetuned from model**: [Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
+
+## Inference Guidelines
 
 
 ```python
 import transformers
 import torch
 
-model_id = "yodayo-ai/nephra_v1.0"
+model_id = "yodayo-ai/Nephra_V1.0"
 
 pipeline = transformers.pipeline(
   "text-generation",
@@ -51,7 +59,7 @@ print(outputs[0]["generated_text"][len(prompt):])
 
 ### Recommended Settings
 
-To guide the model towards generating high quality responses, here are the ideal settings:
+To guide the model to generate high-quality responses, here are the ideal settings:
 
 ```
 Prompt Format: Same Prompt Format as Llama-3-Instruct
@@ -62,5 +70,30 @@ Custom Stopping Strings: "\n{{user}}", "<" , "```" , -> Has occasional broken ge
 ```
 
 
-nephra v1 falls under [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE).
+## Training 
+
+These are the key hyperparameters used during training:
+
+| Hyperparameters                       | Finetuning              |
+|-------------------------------|----------------------------|
+| **Hardware**                  | 4x Nvidia L40 48GB        |
+| **Batch Size**                | 4x 2                         |
+| **Gradient Accumulation Steps** | 4x 3                        |
+| **LoRA Rank**              | 32                      |
+| **LoRA Alpha**              | 64                       |
+| **LoRA Dropout**              | 0.04                       |
+| **Seq_Length**              | 8192                       |
+| **LoRA Target Layers**              | All Linear Layers                      |
+| **Epochs**                    | 2                         |
+| **Max Learning Rate**        | 2e-4                       |
+| **Min Learning Rate** | 4e-5                   |
+| **Optimizer**                 | adamw_bnb_8bit                 |
+| **Optimizer Args**            | Warmup: True | Steps: 20
+| **Scheduler**                 | cosine_with_min_lr      |
+| **Warmup Steps**              | 4%                       |
+
+## License
+
+Nephra v1 falls under [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE).
 
+to