Update README.md

README.md

@@ -1,28 +1,23 @@
 ---
-
+model_name: GPT-OSS AgentBoi
 base_model: unsloth/gpt-oss-20b-unsloth-bnb-4bit
 license: apache-2.0
-
 language:
-
-* en
-
+  - en
 tags:
-
-* gpt-oss
-* agent
-* tool-calling
-* react
-* lora
-* unsloth
-* trl
-* reasoning
-* harmony
-* text-generation
-
+  - gpt-oss
+  - agent
+  - tool-calling
+  - react
+  - lora
+  - unsloth
+  - trl
+  - reasoning
+  - harmony
+  - text-generation
 pipeline_tag: text-generation
-
-## library_name: transformers
+library_name: transformers
+---
 
 # GPT-OSS AgentBoi
 
@@ -34,27 +29,27 @@ This model was fine-tuned using LoRA adapters on the ReAct subset of Agent-FLAN
 
 Large language models are often strong conversationalists but can struggle with:
 
-* Multi-step planning
-* Tool selection and invocation
-* ReAct-style reasoning workflows
-* Structured action generation
-* Separating reasoning from final responses
+- Multi-step planning
+- Tool selection and invocation
+- ReAct-style reasoning workflows
+- Structured action generation
+- Separating reasoning from final responses
 
 GPT-OSS AgentBoi adapts GPT-OSS-20B toward these agent-oriented tasks while remaining trainable on consumer hardware through parameter-efficient fine-tuning.
 
 ## Model Details
 
-| Item            | Value                                |
-| --------------- | ------------------------------------ |
-| Model Name      | GPT-OSS AgentBoi                     |
-| Author          | shiv207                              |
-| Base Model      | unsloth/gpt-oss-20b-unsloth-bnb-4bit |
-| Training Method | LoRA                                 |
-| Framework       | Unsloth                              |
-| Dataset         | Agent-FLAN (ReAct subset)            |
-| Primary Task    | Agentic Tool Use                     |
-| Language        | English                              |
-| License         | Apache 2.0                           |
+| Item | Value |
+|--------|--------|
+| Model Name | GPT-OSS AgentBoi |
+| Author | shiv207 |
+| Base Model | unsloth/gpt-oss-20b-unsloth-bnb-4bit |
+| Training Method | LoRA |
+| Framework | Unsloth |
+| Dataset | Agent-FLAN (ReAct subset) |
+| Primary Task | Agentic Tool Use |
+| Language | English |
+| License | Apache 2.0 |
 
 ## Training Data
 
@@ -62,21 +57,21 @@ The model was fine-tuned using examples from the Agent-FLAN dataset, specificall
 
 These examples teach the model to:
 
-* Break complex tasks into intermediate steps
-* Decide when tool usage is appropriate
-* Generate structured actions
-* Follow action-observation loops
-* Produce concise final responses
+- Break complex tasks into intermediate steps
+- Decide when tool usage is appropriate
+- Generate structured actions
+- Follow action-observation loops
+- Produce concise final responses
 
 ## Training Setup
 
 Training was performed using:
 
-* GPT-OSS-20B
-* Unsloth
-* TRL
-* LoRA adapters
-* Google Colab Tesla T4 GPU
+- GPT-OSS-20B
+- Unsloth
+- TRL
+- LoRA adapters
+- Google Colab Tesla T4 GPU
 
 The objective was to improve agentic behavior while keeping training accessible on limited hardware.
 
@@ -84,20 +79,20 @@ The objective was to improve agentic behavior while keeping training accessible
 
 This model is intended for:
 
-* AI agents
-* Tool-calling systems
-* Research assistants
-* Retrieval-augmented generation workflows
-* Multi-step planning tasks
-* Agentic reasoning experiments
+- AI agents
+- Tool-calling systems
+- Research assistants
+- Retrieval-augmented generation workflows
+- Multi-step planning tasks
+- Agentic reasoning experiments
 
 Potential applications include:
 
-* Search agents
-* Knowledge retrieval systems
-* Function-calling assistants
-* Research copilots
-* Workflow automation agents
+- Search agents
+- Knowledge retrieval systems
+- Function-calling assistants
+- Research copilots
+- Workflow automation agents
 
 ## Example
 
@@ -109,11 +104,11 @@ Search for the latest SpaceX launch and summarize it.
 
 ### Expected Agent Behavior
 
-1. Analyze the request
-2. Determine that external information is required
-3. Generate a structured search action
-4. Process retrieved information
-5. Produce a concise final answer
+1. Analyze the request.
+2. Determine that external information is required.
+3. Generate a structured search action.
+4. Process retrieved information.
+5. Produce a concise final answer.
 
 The fine-tuning objective is to increase consistency in these workflows compared to the base model.
 
@@ -129,22 +124,28 @@ model, tokenizer = FastLanguageModel.from_pretrained(
 
 ## Limitations
 
-* Evaluated primarily through qualitative testing.
-* No formal benchmark suite was used.
-* Training utilized only a subset of Agent-FLAN.
-* Performance may vary on unseen tool schemas.
-* Not optimized for general-purpose instruction tuning beyond agent-oriented tasks.
+- Evaluated primarily through qualitative testing.
+- No formal benchmark suite was used.
+- Training utilized only a subset of Agent-FLAN.
+- Performance may vary on unseen tool schemas.
+- Not optimized for general-purpose instruction tuning beyond agent-oriented tasks.
 
 ## Acknowledgments
 
 This project builds upon the work of:
 
-* OpenAI for GPT-OSS and the Harmony conversation format
-* Unsloth for efficient GPT-OSS fine-tuning support
-* InternLM for the Agent-FLAN dataset
+- OpenAI for GPT-OSS and the Harmony conversation format.
+- Unsloth for efficient GPT-OSS fine-tuning support.
+- InternLM for the Agent-FLAN dataset.
+
+## Repository
+
+Source code and training notebook:
+
+GitHub: https://github.com/shiv207
 
 ## Author
 
 **shiv207**
 
-If you find this project useful, feel free to open issues, share feedback, or build on top of it.
+If you find this project useful, feel free to open issues, share feedback, or build on top of it.