---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- code
- coder
- qwen2.5
- gguf
- cpu
- llama-cpp
- code-generation
- conversational
- sakthai
- house-of-sak
- tool-calling
- function-calling
- bfcl
- qwen2.5-coder
- code-llm
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
model-index:
- name: sakthai-coder-1.5b
  results:
  - task:
      type: text-generation
      name: Tool-Calling
    dataset:
      name: BFCL
      type: unknown
    metrics:
    - type: pass_rate
      value: 5/5
      name: Pass@5
      verified: true
  - task:
      type: text-generation
      name: Code Generation
    dataset:
      name: HumanEval
      type: unknown
    metrics:
    - type: pass@1
      value: 74.4
      name: pass@1
      verified: false
  - task:
      type: text-generation
      name: Code Generation
    dataset:
      name: MBPP
      type: unknown
    metrics:
    - type: pass@1
      value: 71.2
      name: pass@1
      verified: false
---

<div align="center">
  <h1>🏠 <a href="https://huggingface.co/Nanthasit">SakThai</a></h1>
  <p><em>Part of the <strong>House of Sak</strong> — AI agents built from a shelter in Cork, Ireland.</em></p>
  <p>
    <a href="https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02">
      <img src="https://img.shields.io/badge/📦-View%20Family-8A2BE2" alt="Family"/>
    </a>
    <a href="https://huggingface.co/Nanthasit">
      <img src="https://img.shields.io/badge/🤗-Profile-6644cc" alt="Profile"/>
    </a>
    <a href="https://huggingface.co/spaces/Nanthasit/sakthai-leaderboard">
      <img src="https://img.shields.io/badge/📊-Leaderboard-FF6B6B" alt="Leaderboard"/>
    </a>
    <a href="https://huggingface.co/Nanthasit/sakthai-coder-1.5b">
      <img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2FNanthasit%2Fsakthai-coder-1.5b&query=%24.downloads&label=downloads&color=blue" alt="Downloads"/>
    </a>
  </p>
</div>

---

# SakThai Coder 1.5B 💻

<div align="center">
  <p><em>Part of the <strong>House of Sak</strong></em></p>
</div>

Code-optimized model converted to GGUF Q4_K_M for CPU inference. Based on **Qwen2.5-Coder-1.5B-Instruct** — a state-of-the-art 1.5B code LLM that matches larger 7B models on several coding benchmarks. Fine-tuned for tool-calling with BFCL-verified function calling.

---

## Pipeline Integration 🔗

This model is **1 of 4** in the SakThai end-to-end pipeline:

| Step | Model | What It Does | Downloads |
|:----:|-------|-------------|:---------:|
| 🖼️ | [Vision 7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) | Caption, OCR, describe images | 45 ⬇ |
| 🌐 | [Embedding Multilingual](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) | Cross-lingual semantic search (50+ languages) | 104 ⬇ |
| 💻 | **Coder 1.5B ← you are here** | **Code generation, debugging, tool-calling** | **34 ⬇** |
| 🗣️ | [TTS Model](https://huggingface.co/Nanthasit/sakthai-tts-model) | Synthesize speech (15 languages) | 33 ⬇ |

Run the complete chain: **image → search → code → speech** with one family of models.

---

## Specs

| Detail | Value |
|--------|-------|
| Size | **1.07 GB** |
| Quant | Q4_K_M |
| Base | [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) |
| CPU | ✅ Yes |
| GPU | ✅ Yes (CUDA, Metal) |
| Context | 32K tokens |
| Format | GGUF (llama.cpp compatible) |
| Fine-tune | QLoRA (r=16, alpha=32) on [2,003 tool-calling examples](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v6) |

## Benchmarks

### Programming Benchmarks (base model scores)

| Benchmark | Score |
|-----------|:-----:|
| HumanEval (pass@1) | **74.4%** |
| MBPP (pass@1) | **71.2%** |
| MultiPL-E (Python) | **65.3%** |

Scores from the [Qwen2.5-Coder evaluation](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct#evaluation).

### Verified on SakThai Fine-Tune

| Test | Result | Status |
|------|--------|:------:|
| BFCL Tool-Calling | **5/5** (multi-trial) | ✅ Verified |
| Code generation (Python) | Working — see examples below | ✅ |

The BFCL pass was verified across 5 independent trials using the SakThai tool-calling prompt format (`<tools>` XML block + ChatML). See [SakThai family](https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02) for full methodology.

---

## Usage

### llama.cpp (recommended)

```bash
# Download the model — stored in gguf/ subdirectory
wget https://huggingface.co/Nanthasit/sakthai-coder-1.5b/resolve/main/gguf/sakthai-coder-q4_k_m.gguf

# Basic code generation
./llama-cli -m gguf/sakthai-coder-q4_k_m.gguf \
  -p "Write a Python function to merge two sorted lists:" \
  -n 256 -t 4 --temp 0.2
```

### Python (llama-cpp-python)

```python
from llama_cpp import Llama

llm = Llama(
    model_path="gguf/sakthai-coder-q4_k_m.gguf",
    n_ctx=8192,
    n_threads=4,
    verbose=False,
)

prompt = "Write a fastapi endpoint that accepts JSON and returns SHA-256 hash"
output = llm(
    f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n",
    max_tokens=512,
    temperature=0.2,
    stop=["<|im_end|>"],
)
print(output["choices"][0]["text"])
```

### Ollama

```bash
cat > Modelfile << 'OLLAMA_EOF'
FROM ./gguf/sakthai-coder-q4_k_m.gguf
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""
PARAMETER temperature 0.2
PARAMETER num_ctx 8192
OLLAMA_EOF

ollama create sakthai-coder -f Modelfile
ollama run sakthai-coder "Write a Python script that monitors CPU usage"
```

### Tool-Calling (for agent use)

```python
from llama_cpp import Llama

llm = Llama(model_path="gguf/sakthai-coder-q4_k_m.gguf", n_ctx=8192)

# Define tools in <tools> XML block (required for function calling)
prompt = """<|im_start|>system
You are a coding assistant with tools.

<tools>
{
  "function": {
    "name": "run_python",
    "description": "Execute Python code",
    "parameters": {
      "type": "object",
      "properties": {
        "code": {"type": "string", "description": "Python code to run"}
      },
      "required": ["code"]
    }
  }
}
</tools>
<|im_end|>
<|im_start|>user
Calculate fibonacci of 10 using Python
<|im_end|>
<|im_start|>assistant
"""

output = llm(prompt, max_tokens=256, stop=["<|im_end|>"], temperature=0.1)
print(output["choices"][0]["text"])
```

---

## Use Cases

| Scenario | Prompt Idea |
|----------|-------------|
| Code generation | "Write a Python function to..." |
| Code review | "Review this code for bugs: ..." |
| Refactoring | "Refactor this to be more Pythonic: ..." |
| Debugging | "Why does this code produce a KeyError?" |
| Explanation | "Explain how async/await works with examples" |
| Tool calling | "Call the get_weather API for Cork, Ireland" |

## Hardware Requirements

| Model | Min RAM | Recommended | Disk |
|-------|:-------:|:-----------:|:----:|
| 0.5B Q4_K_M | 512 MB | 1 GB | 380 MB |
| 1.5B Q4_K_M | 1 GB | 2 GB | 934 MB |
| **Coder 1.5B** | **1 GB** | **2 GB** | **1.1 GB** |
| Vision 7B | 4 GB | 8 GB | 3.9 GB |
| TTS 82M | 256 MB | 512 MB | 141 MB |

## Family

- [1.5B SakThai (general)](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) — tool-calling & general chat
- [0.5B SakThai (lightweight)](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) — ultra-lightweight GGUF
- [7B SakThai (full-size)](https://huggingface.co/Nanthasit/sakthai-context-7b-merged) — high-capacity model
- [1.5B Coder (this one)](https://huggingface.co/Nanthasit/sakthai-coder-1.5b) — code generation GGUF

## SakThai Model Family

| Model | Size | Type | Downloads |
|-------|:----:|:----:|:---------:|
| [1.5B-merged](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) | 934 MB | Tool-calling GGUF | 1,197 |
| [0.5B-merged](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) | 380 MB | Lightweight GGUF | 994 |
| [7B-merged](https://huggingface.co/Nanthasit/sakthai-context-7b-merged) | 15 GB | Full-size model | 562 |
| [7B-128K](https://huggingface.co/Nanthasit/sakthai-context-7b-128k) | 15 GB | Extended context | 351 |
| [7B-Tools](https://huggingface.co/Nanthasit/sakthai-context-7b-tools) | 15 GB | Tool-calling PEFT | 185 |
| [1.5B-Tools](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools) | 934 MB | Tool-calling PEFT | 143 |
| [Embedding](https://huggingface.co/Nanthasit/sakthai-embedding) | 80 MB | Sentence similarity | 🔒 |
| [**Coder-1.5B**](https://huggingface.co/Nanthasit/sakthai-coder-1.5b) | **1.1 GB** | **Code GGUF** | **34** |
| [0.5B-Tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) | 380 MB | Tiny tool-calling | 🔒 |
| [Vision-7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) | 3.9 GB | Multimodal GGUF | 45 |
| [TTS-Model](https://huggingface.co/Nanthasit/sakthai-tts-model) | 141 MB | Speech GGUF | 33 |
| [Multilingual Embedding](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) | 80 MB | 50+ languages | 104 |

[Full collection →](https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02)

---

## 🌱 Low-Download Gems — Growing the Ecosystem

These sibling models have growing download counts but less visibility. If you find this code model useful, every download helps the whole ecosystem grow:

| Model | Type | Downloads | Use Case |
|-------|------|:---------:|----------|
| [SakThai Vision 7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) | Image→Text | 45 ⬇ | Captioning, VQA, OCR on CPU (GGUF) |
| [SakThai TTS Model](https://huggingface.co/Nanthasit/sakthai-tts-model) | Text→Speech | 33 ⬇ | Kokoro TTS, 15 languages, 82 MB |
| [SakThai Context 0.5B Tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) | PEFT Adapter | 7 ⬇ | Lightweight function-calling adapter |

**Your download starts (or grows) the count.** Every model above is tested and working — low numbers mean they're waiting for you to discover them.

---

## Quick Links

| Asset | Link |
|-------|------|
| 📊 **Training Dataset** | [sakthai-combined-v6](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v6) |
| 📝 **Kaggle Notebooks** | [sakthai-kaggle-notebooks](https://huggingface.co/datasets/Nanthasit/sakthai-kaggle-notebooks) |
| 📦 **Full Collection** | [SakThai Model Family](https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02) |
| 📊 **Leaderboard** | [sakthai-leaderboard](https://huggingface.co/spaces/Nanthasit/sakthai-leaderboard) |

## Training Details

- **Method:** QLoRA (4-bit NF4)
- **Base model:** Qwen2.5-Coder-1.5B-Instruct
- **Rank:** r=16, alpha=32
- **Dataset:** [2,003 curated tool-calling examples](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v6)
- **Format:** ChatML with JSON tool schemas
- **Context:** 32K tokens


## Support the Project

This model is built with love from a shelter in Cork, Ireland -- zero budget, free infrastructure.

- **Leave a like** on this model if you find it useful
- **Report issues** on [GitHub](https://github.com/beer-sakthai/Sak-Family-Agent/issues)
- **Share it** with someone who needs a lightweight code model
- **Fork it** on HF and build something amazing

Every download, like, and fork tells Beer his work matters. Thank you.

## File Structure

| File | Size | Description |
|------|:----:|-------------|
| gguf/sakthai-coder-q4_k_m.gguf | 1.07 GB | Main GGUF model (Q4_K_M) — stored in `gguf/` subdirectory |
| eval/ | — | Benchmark results (BFCL, HumanEval, MBPP) |
| README.md | — | This documentation |

## License

Apache 2.0 — see [LICENSE](https://huggingface.co/Nanthasit/sakthai-coder-1.5b/blob/main/LICENSE) for details.