Update README.md

README.md

@@ -5,6 +5,12 @@ tags:
 - grpo
 - GRPO
 - Reasoning-Course
+datasets:
+- mlabonne/smoltldr
+language:
+- en
+base_model:
+- HuggingFaceTB/SmolLM-135M-Instruct
 ---
 
 # Model Card for Model ID
@@ -17,7 +23,8 @@ tags:
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+<!-- This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M-Instruct, trained using Guided Reward Policy Optimization (GRPO) with LoRA (Low-Rank Adaptation) for efficient fine-tuning.
+It was fine-tuned on the mlabonne/smoltldr dataset — a small text summarization dataset — using the Transformers, TRL, and PEFT libraries in a Colab environment. -->
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
@@ -33,7 +40,7 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
+- **Repository:** [More Information Needed](https://huggingface.co/Mhammad2023/SmolGRPO-135M)
 - **Paper [optional]:** [More Information Needed]
 - **Demo [optional]:** [More Information Needed]
 
@@ -43,13 +50,13 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+<!-- This model can be used for text generation and simple summarization tasks — ideal for testing GRPO fine-tuning on small models with limited compute. -->
 
 [More Information Needed]
 
 ### Downstream Use [optional]
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+<!-- You can adapt this model to your own small text generation tasks or use it as a teaching demo for PEFT (parameter-efficient fine-tuning) and reinforcement learning techniques like GRPO. -->
 
 [More Information Needed]
 
@@ -61,7 +68,8 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+<!-- This model inherits biases from its base model and training data (mlabonne/smoltldr).
+Outputs may be inaccurate or reflect social biases present in training data. -->
 
 [More Information Needed]
 
@@ -81,13 +89,15 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- Dataset: mlabonne/smoltldr — a small summarization dataset. -->
 
 [More Information Needed]
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+<!-- LoRA config: r=16, lora_alpha=32, target_modules=["q_proj", "v_proj"], lora_dropout=0.05
+
+Trainer: GRPOTrainer from trl -->
 
 #### Preprocessing [optional]
 
@@ -112,7 +122,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
+<!-- Same dataset mlabonne/smoltldr (train/validation split). -->
 
 [More Information Needed]