Update README.md

README.md

@@ -7,17 +7,49 @@ tags:
 - qwen3
 - trl
 - sft
-license: apache-2.0
+license: agpl-3.0
 language:
 - en
+datasets:
+- marcuscedricridia/finetome-score-gte-4p5-only
+- marcuscedricridia/wizard_vicuna_70k_unfiltered-deepclean-sharegpt
+- marcuscedricridia/ultrafeedback-chosen-rating-eq-5
 ---
 
-# Uploaded  model
+## Overview
 
-- **Developed by:** marcuscedricridia
-- **License:** apache-2.0
-- **Finetuned from model :** marcuscedricridia/kgr-600m-2511-it-616
+`kgr-600m-2511-it-709` is a 600M parameter language model fine-tuned for general instruction-following tasks. It is part of the KGR family, designed to be lightweight and efficient while maintaining strong performance on practical prompts.
 
-This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+## Intended Use
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+This model is built for general-purpose instruction tasks such as:
+
+- Question answering  
+- Summarization  
+- Short-form generation  
+- Instruction completion  
+
+It performs best when given clear, direct prompts.
+
+## Inference Settings
+
+Recommended parameters for sampling:
+
+- `temperature = 0.3`  
+- `min_p = 0.01`  
+- `repetition_penalty = 1.2`  
+- `top_p = 0.95`  
+- `top_k = 100` (values of 20 or 40 are also valid)
+
+A repetition penalty is used due to the model’s smaller size. It helps prevent looping and improves output coherence.
+
+## Special Notes
+
+- The `enable_thinking = true/false` parameter no longer affects behavior when toggled. This flag was overridden during training.
+- However, the **idea behind** `enable_thinking`—encouraging chain-of-thought reasoning—is still functional when prompted explicitly. Asking the model to "think step by step" or using similar phrasing can activate this behavior.
+
+## Limitations
+
+- Struggles with complex multi-step reasoning.
+- Not suitable for high-stakes or sensitive applications.
+- Outputs may occasionally reflect training biases or limitations in generalization.