Upload README.md with huggingface_hub

README.md

@@ -1,37 +1,173 @@
-# nodejs-coder-qwen25
+---
+language:
+- en
+license: apache-2.0
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- qwen2
+- trl
+- nodejs
+- javascript
+- backend
+- express
+- gguf
+- ollama
+pipeline_tag: text-generation
+---
 
-A fine-tuned **Qwen2.5-Coder-7B** model specialized for Node.js backend development, merged and quantized to GGUF (Q4_K_M) for local inference with Ollama.
+# 🚀 nodejs-coder-qwen25
 
-## Model Details
-- **Base Model:** `unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit`
-- **Fine-tuning:** LoRA adapters merged into base weights
-- **Format:** GGUF Q4_K_M (~4.4 GB)
-- **Specialties:** Express.js, NestJS, Sequelize, Prisma, MongoDB, PostgreSQL, Jest
+A fine-tuned **Qwen2.5-Coder-7B-Instruct** model specialized for **Node.js backend development**, trained with LoRA adapters using Unsloth, merged into a single GGUF file for efficient local inference with Ollama.
 
-## Quick Start with Ollama
+---
 
+## 🧠 Model Description
+
+| Property | Details |
+|----------|---------|
+| **Base Model** | `Qwen2.5-Coder-7B-Instruct` |
+| **Fine-tuning Method** | LoRA (Low-Rank Adaptation) via Unsloth |
+| **Training Framework** | TRL SFTTrainer |
+| **Quantization** | GGUF Q4_K_M (~4.4 GB) |
+| **Context Length** | 2048 tokens |
+| **Language** | JavaScript / Node.js |
+
+This model is specifically trained to write clean, production-ready Node.js backend code. It understands common backend patterns including REST APIs, database integrations, authentication, and testing.
+
+---
+
+## 🎯 Specialties
+
+- ✅ **Express.js** — REST APIs, middleware, routing
+- ✅ **NestJS** — modules, controllers, services, guards
+- ✅ **Sequelize / Prisma** — ORM models, migrations, queries
+- ✅ **MongoDB / Mongoose** — schemas, models, aggregations
+- ✅ **PostgreSQL / pg** — raw queries, connection pooling
+- ✅ **JWT Authentication** — login, token generation, guards
+- ✅ **Jest** — unit tests, mocking, integration tests
+- ✅ **Async/Await** — file I/O, error handling, promises
+
+---
+
+## ⚡ Quick Start with Ollama
+
+### Step 1 — Download files
 ```bash
-# 1. Download the GGUF
 hf download Sriram-214/nodejs-coder-qwen25 nodejs-coder-Q4_K_M.gguf --local-dir ./
-
-# 2. Download the Modelfile
 hf download Sriram-214/nodejs-coder-qwen25 Modelfile --local-dir ./
+```
 
-# 3. Create the Ollama model
+### Step 2 — Create Ollama model
+```bash
 ollama create nodejs-coder -f Modelfile
+```
 
-# 4. Run it
+### Step 3 — Run
+```bash
 ollama run nodejs-coder
 ```
 
-## Modelfile Configuration
-The included `Modelfile` uses the correct **Qwen2 chat template** with proper stop tokens.
-For GPUs with limited VRAM (≤6GB), `num_gpu 0` forces CPU inference.
+---
+
+## 📋 Modelfile
+
+```dockerfile
+FROM ./nodejs-coder-Q4_K_M.gguf
+
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER repeat_penalty 1.1
+PARAMETER num_ctx 2048
+PARAMETER num_gpu 0
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "<|im_start|>"
 
-## Example Prompts
+TEMPLATE """<|im_start|>system
+{{ .System }}<|im_end|>
+<|im_start|>user
+{{ .Prompt }}<|im_end|>
+<|im_start|>assistant
+"""
+
+SYSTEM """You are a Node.js backend development expert. You write clean, efficient, production-ready code following best practices. You specialize in Express.js, NestJS, Sequelize, Prisma, MongoDB, PostgreSQL, and Jest testing. Always include error handling and follow RESTful API design principles."""
 ```
-Write a Node.js REST API with Express and JWT authentication
-Create a Mongoose model for a User with name, email and age
-Write a pg query to fetch paginated users with error handling
-Write Jest unit tests for an Express route handler
+
+> **Note:** Set `num_gpu 0` for CPU-only mode on GPUs with ≤6GB VRAM. For GPUs with more VRAM, increase this value.
+
+---
+
+## 💬 Example Prompts & Outputs
+
+### Express REST API
+**Prompt:** `Write a simple Express.js REST API with a GET /health endpoint`
+
+```javascript
+const express = require('express');
+const app = express();
+
+app.get('/health', (req, res) => {
+  res.status(200).json({ status: 'ok' });
+});
+
+app.listen(3000, () => console.log('Server running on port 3000'));
+```
+
+### Async File Reading
+**Prompt:** `Write a Node.js function that reads a JSON file using async/await`
+
+```javascript
+const fs = require('fs').promises;
+
+async function readJsonFile(filePath) {
+  try {
+    const data = await fs.readFile(filePath, 'utf-8');
+    return JSON.parse(data);
+  } catch (error) {
+    throw new Error(`Failed to read file: ${error.message}`);
+  }
+}
+```
+
+### List Directory Files
+**Prompt:** `Write a simple Node.js code to list all the files in a directory`
+
+```javascript
+const fs = require('fs');
+
+fs.readdir('./', (err, files) => {
+  if (err) throw err;
+  console.log(files);
+});
 ```
+
+---
+
+## 🏋️ Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| **Base Model** | `unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit` |
+| **LoRA Rank** | 16 |
+| **LoRA Alpha** | 32 |
+| **Training Data** | Node.js backend code dataset |
+| **Training Framework** | Unsloth + TRL SFTTrainer |
+| **Training Environment** | Google Colab (T4 GPU) |
+| **Quantization** | Q4_K_M via llama.cpp |
+
+---
+
+## ⚠️ Limitations
+
+- Optimized for Node.js/JavaScript — not suited for other languages
+- Context window of 2048 tokens — long files may be truncated
+- CPU inference is slow (~3-5 tokens/sec on modern CPUs)
+- May occasionally produce outdated library syntax
+
+---
+
+## 📄 License
+
+Apache 2.0 — see [LICENSE](https://www.apache.org/licenses/LICENSE-2.0)