Update README.md

README.md

@@ -14,7 +14,6 @@ tags:
 - gguf
 - ollama
 - 3b
-- function-calling
 license: apache-2.0
 base_model: Qwen/Qwen2.5-3B-Instruct
 datasets:
@@ -26,43 +25,98 @@ datasets:
 
 # 🤖 LaboAI-0.3.3-3B
 
-This is a versatile, 3-billion parameter language model heavily fine-tuned for **Kotlin** and **Android** development, while retaining strong general-purpose capabilities. 
+This is a mid-sized language model (3B parameters) fine-tuned specifically for generating, understanding, and debugging **Kotlin** code and **Android** development (with a strong emphasis on Jetpack Compose, Coroutines, and modern architectures). 
 
-Built on the robust `Qwen2.5-3B-Instruct` architecture, this model underwent a massive, high-quality fine-tuning regimen (v0.3.3). It excels at generating, understanding, and debugging modern Android code (Jetpack Compose, Coroutines, MVVM) but remains highly capable in general chat, reasoning, and tool-calling tasks.
+This version (0.3.3) shares the same training recipe as the 1.5B variant but leverages the increased capacity of the 3B base model for superior reasoning, better handling of complex code structures, and improved generalization across diverse Android development scenarios. It is optimized using **QLoRA (4-bit)** to run efficiently on consumer GPUs with 6-8GB VRAM.
 
 ## 📋 Model Details
 
 - **Developed by:** Mmxa
 - **Organization:** LaboAI
-- **Model type:** Causal Language Model (Code Generation & General Assistant)
-- **Languages:** Kotlin, Java, English, Spanish
+- **Model type:** Causal Language Model (Code Generation)
+- **Languages:** Kotlin, Java, English, Spanish (instructions)
 - **License:** Apache 2.0 (inherited from Qwen2.5)
 - **Base model:** [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)
 
 ## 🚀 Uses
 
 ### Direct Use
-- **Android Development:** Generating boilerplate, Jetpack Compose UIs, ViewModels, and debugging Kotlin code.
-- **General Assistant:** Answering questions, summarizing text, and logical reasoning.
-- **Tool Calling:** Capable of structured JSON output for function calling and agentic workflows.
+- Generating boilerplate for Activities, Fragments, ViewModels, and Repositories in Kotlin.
+- Creating modern UI components with **Jetpack Compose**.
+- Debugging compilation errors or logic flaws in Android code snippets.
+- Translating legacy Java logic into modern, idiomatic Kotlin.
+- Understanding and explaining complex Android architecture patterns (MVVM, MVI, Clean Architecture).
 
 ### Ecosystem Use (Recommended)
-This model is optimized for local inference via **Ollama** and integrates seamlessly with the **Continue** extension in VS Code. It strikes the perfect balance between intelligence and local hardware efficiency.
+This model shines when used as a local coding assistant via **Ollama** and the **Continue** extension in VS Code. This guarantees complete privacy (your code never leaves your machine) and low latency.
 
 ### Out-of-Scope Uses
-- It should not be used to generate malicious code, exploits, or harmful content.
-- All generated code must be reviewed by a human developer before deployment.
+- It is not optimized for general chat, creative writing, or complex mathematical reasoning.
+- It should not be used to generate malicious code or exploits.
+- All generated code must be reviewed by a human developer before being merged into a main branch.
 
 ## ⚠️ Limitations and Risks
-- **Context Window:** Optimized for 2048-4096 tokens. It may lose coherence in extremely long, multi-file contexts.
-- **API Hallucinations:** In rare cases, it might suggest slightly deprecated Android APIs.
-- **General Knowledge:** While fine-tuned for code, its general world knowledge is bounded by its base model and the fine-tuning data distribution.
+- **API Hallucinations:** In rare cases, it might suggest deprecated Android APIs instead of modern alternatives.
+- **Context Window:** Optimized for 2048 tokens. It is not suitable for analyzing massive, multi-thousand-line codebase files all at once.
+- **Dependencies:** It does not have real-time knowledge of the latest Android library updates.
 
-##  How to Get Started (Local Setup)
+## 💻 How to Get Started (Local Setup)
 
-This repository includes both the original format (`safetensors`) and the quantized format (`GGUF` Q4_K_M). 
+This repository includes both the original format (`safetensors`) and the quantized format (`GGUF` Q4_K_M). To use it on your PC with a 6-8GB VRAM GPU:
 
-### Quick Start with Ollama
-The fastest way to run this model is directly from Hugging Face via Ollama:
-```bash
-ollama run hf.co/LaboAI/LaboAI-0.3.3-3B:Q4_K_M
+1. Install [Ollama](https://ollama.com/).
+2. Download the `.gguf` file from this repository (e.g., `LaboAI-0.3.3-3B-Q4_K_M.gguf`).
+3. Create a file named `Modelfile` in the same folder with the following content:
+   ```text
+   FROM ./LaboAI-0.3.3-3B-Q4_K_M.gguf
+   TEMPLATE """{{- if .Messages }}
+   {{- if or .System .Tools }}<|im_start|>system
+   {{- if .System }}
+   {{ .System }}
+   {{- end }}
+   {{- if .Tools }}
+
+   # Tools
+
+   You may call one or more functions to assist with the user query.
+
+   You are provided with function signatures within <tools></tools> XML tags:
+   <tools>
+   {{- range .Tools }}
+   {"type": "function", "function": {{ .Function }}}
+   {{- end }}
+   </tools>
+
+   For each function call, return a json object with function name and arguments within  XML tags:
+   
+   {{- end }}<|im_end|>
+   {{ end }}
+   {{- range $i, $_ := .Messages }}
+   {{- $last := eq (len (slice $.Messages $i)) 1 -}}
+   {{- if eq .Role "user" }}<|im_start|>user
+   {{ .Content }}<|im_end|>
+   {{ else if eq .Role "assistant" }}<|im_start|>assistant
+   {{ if .Content }}{{ .Content }}
+   {{- else if .ToolCalls }}
+   {{- end }}{{ if not $last }}<|im_end|>
+   {{ end }}
+   {{- else if eq .Role "tool" }}<|im_start|>user
+   <tool_response>
+   {{ .Content }}
+   </tool_response><|im_end|>
+   {{ end }}
+   {{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+   {{ end }}
+   {{- end }}
+   {{- else }}
+   {{- if .System }}<|im_start|>system
+   {{ .System }}<|im_end|>
+   {{ end }}{{ if .Prompt }}<|im_start|>user
+   {{ .Prompt }}<|im_end|>
+   {{ end }}<|im_start|>assistant
+   {{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
+   PARAMETER stop "<|im_end|>"
+   PARAMETER stop "<|endoftext|>"
+   PARAMETER temperature 0.7
+   PARAMETER min_p 0.1
+   SYSTEM """You are LaboAI, a helpful assistant specialized in Kotlin and Android development."""