Update README.md

README.md

@@ -2,56 +2,204 @@
 language: en
 license: apache-2.0
 tags:
-- code
-- coding-agent
-- instruction-tuned
-- hermit-code
+  - code
+  - coding-agent
+  - instruction-tuned
+  - hermit-code
 pipeline_tag: text-generation
-base_model:
-- Qwen/Qwen2.5-Coder-7B-Instruct
 ---
 
-# Hermit Code 7B
+<p align="center">
+  <img src="https://img.shields.io/badge/Parameters-7.6B-blue?style=flat-square" alt="Parameters"/>
+  <img src="https://img.shields.io/badge/Context-128K-green?style=flat-square" alt="Context"/>
+  <img src="https://img.shields.io/badge/License-Apache%202.0-yellow?style=flat-square" alt="License"/>
+  <img src="https://img.shields.io/badge/Format-Safetensors-orange?style=flat-square" alt="Format"/>
+  <img src="https://img.shields.io/badge/Python-3.10%2B-blue?style=flat-square" alt="Python"/>
+</p>
 
-**Hermit Code** is the official coding model for the [Hermit AI Agent](https://github.com/Soloman2002/hermit-agent).
+<h1 align="center">Hermit Code 7B</h1>
+<p align="center"><em>The official coding model for the Hermit AI Agent</em></p>
+
+<p align="center">
+  <a href="#-quick-start">Quick Start</a> •
+  <a href="#-capabilities">Capabilities</a> •
+  <a href="#-model-details">Model Details</a> •
+  <a href="#-usage">Usage</a> •
+  <a href="#-examples">Examples</a> •
+  <a href="#-acknowledgments">Acknowledgments</a>
+</p>
+
+---
+
+## Quick Start
+
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="Soloman2002/hermit-code-7b")
+chat = [
+    {"role": "user", "content": "Write a Python function to reverse a linked list"}
+]
+pipe(chat, max_new_tokens=512)
+```
+
+## Capabilities
+
+| Category | Languages / Skills |
+|---|---|
+| **Languages** | Python, JavaScript/TypeScript, Go, Rust, C++, Java |
+| **Code Gen** | Functions, classes, scripts, full projects |
+| **Explain** | Code breakdowns, documentation generation |
+| **Debug** | Bug finding, fixing, optimization |
+| **Refactor** | Performance tuning, code cleanup |
+| **Context** | Multi-file project understanding (128K tokens) |
 
 ## Model Details
 
 | Property | Value |
 |---|---|
 | **Base Model** | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) |
-| **Architecture** | Qwen2.5 (Dense Transformer) |
-| **Parameters** | 7.6B |
-| **Context Length** | 128K tokens |
+| **Architecture** | Qwen2.5 Dense Transformer |
+| **Parameters** | 7.61B (6.53B non-embedding) |
+| **Layers** | 28 |
+| **Attention** | GQA (28 Q heads, 4 KV heads) |
+| **Context Length** | 131,072 tokens |
 | **License** | Apache 2.0 |
-| **Format** | Safetensors |
+| **Format** | Safetensors (BF16) |
 
-## Capabilities
+## Usage
 
-- Python, JavaScript, TypeScript, Go, Rust, C++, Java code generation
-- Code explanation and documentation
-- Bug fixing and debugging
-- Refactoring and optimization
-- Multi-file project understanding
+### Transformers
 
-## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+    "Soloman2002/hermit-code-7b",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Soloman2002/hermit-code-7b")
+
+messages = [
+    {"role": "system", "content": "You are Hermit Code, a coding assistant."},
+    {"role": "user", "content": "Write a Rust function that checks if a string is a palindrome."}
+]
+text = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True
+)
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=512)
+response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+print(response)
+```
 
-### Via Hugging Face Inference API
+### vLLM (Recommended for Production)
+
+```bash
+pip install vllm
+vllm serve "Soloman2002/hermit-code-7b"
+```
+
+```bash
+curl -X POST "http://localhost:8000/v1/chat/completions" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "Soloman2002/hermit-code-7b",
+    "messages": [
+      {"role": "user", "content": "Explain closures in JavaScript"}
+    ]
+  }'
+```
+
+### Inference API
 
 ```python
 from huggingface_hub import InferenceClient
 
 client = InferenceClient(token="hf_YOUR_TOKEN")
-
 response = client.text_generation(
     model="Soloman2002/hermit-code-7b",
-    prompt="&lt;|im_start|&gt;user\nWrite a Python function to sort a list&lt;|im_end&gt;\n&lt;|im_start&gt;assistant\n",
+    prompt="<|im_start|>user\nWrite a Go function to merge two sorted arrays<|im_end|>\n<|im_start|>assistant\n",
     max_new_tokens=512,
     temperature=0.2
 )
+```
+
+## Examples
+
+<details>
+<summary><b>Python</b> — Quick Sort</summary>
+
+```python
+def quick_sort(arr):
+    if len(arr) <= 1:
+        return arr
+    pivot = arr[len(arr) // 2]
+    left = [x for x in arr if x < pivot]
+    middle = [x for x in arr if x == pivot]
+    right = [x for x in arr if x > pivot]
+    return quick_sort(left) + middle + quick_sort(right)
+```
+</details>
+
+<details>
+<summary><b>Rust</b> — Palindrome Check</summary>
+
+```rust
+fn is_palindrome(s: &str) -> bool {
+    let chars: Vec<char> = s.chars().filter(|c| c.is_alphanumeric()).collect();
+    let len = chars.len();
+    for i in 0..len / 2 {
+        if chars[i].to_ascii_lowercase() != chars[len - 1 - i].to_ascii_lowercase() {
+            return false;
+        }
+    }
+    true
+}
+```
+</details>
+
+<details>
+<summary><b>Go</b> — Merge Sorted Arrays</summary>
+
+```go
+func mergeSorted(a, b []int) []int {
+    result := make([]int, 0, len(a)+len(b))
+    i, j := 0, 0
+    for i < len(a) && j < len(b) {
+        if a[i] < b[j] {
+            result = append(result, a[i])
+            i++
+        } else {
+            result = append(result, b[j])
+            j++
+        }
+    }
+    result = append(result, a[i:]...)
+    result = append(result, b[j:]...)
+    return result
+}
+```
+</details>
+
+## Benchmarks
+
+| Benchmark | Score |
+|---|---|
+| HumanEval (Python) | TBD |
+| HumanEval (Multi-Lang) | TBD |
+| MBPP | TBD |
+
+*Coming soon — based on Qwen2.5-Coder-7B-Instruct baseline.*
 
 ## Acknowledgments
 
-Original model: [Qwen team](https://huggingface.co/Qwen)
-Hermit AI Agent: Built by the Hermit team
-```
+- **Base Model** — [Qwen Team](https://huggingface.co/Qwen) for [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
+- **Hermit AI Agent** — Built by the [Hermit Team](https://github.com/Soloman2002)
+
+---
+
+<p align="center">
+  <sub>Built with ❤️ for the coding community</sub>
+</p>