---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- qwen2.5
- sakthai
- tool-calling
- instruct
- merged
- lora
- text-generation
- function-calling
datasets:
- Nanthasit/sakthai-combined-v5
base_model: Qwen/Qwen2.5-7B-Instruct
model-index:
- name: sakthai-context-7b-merged
  results:
  - task:
      type: text-generation
      name: Tool-Calling & Instruction Following
    dataset:
      type: Nanthasit/sakthai-combined-v5
      name: SakThai Workbench Eval
    metrics:
    - type: pass_rate
      value: 100
      name: Overall Pass Rate (8/8)
---

# SakThai Context 7B — Merged Model

The best-performing model in the **SakThai Context** family. A full-parameter merged checkpoint of Qwen2.5-7B-Instruct with LoRA adapters fine-tuned for structured tool-calling and instruction following.

**LoRA adapter:** [`Nanthasit/sakthai-context-7b-tools`](https://huggingface.co/Nanthasit/sakthai-context-7b-tools)  
**Training data:** [`Nanthasit/sakthai-combined-v5`](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v5)

## Model Details

| Property | Value |
|---|---|
| **Developed by** | Nanthasit |
| **Base model** | [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) |
| **Parameters** | 7.6B |
| **Architecture** | Qwen2.5 decoder-only transformer |
| **Precision** | BF16 |
| **Fine-tuning method** | LoRA → merged (rank=16, alpha=32, target=q/k/v/o/gate/up/down) |
| **License** | Apache 2.0 |

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "Nanthasit/sakthai-context-7b-merged",
    torch_dtype="bfloat16",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-context-7b-merged")

messages = [{"role": "user", "content": "What's the weather like in Bangkok?"}]
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=256, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### Tool Calling

The model supports structured tool-calling via Qwen2.5's tokenizer tool schema:

```python
messages = [
    {"role": "system", "content": "You are a helpful assistant with access to tools."},
    {"role": "user", "content": "What's the weather in Bangkok?"}
]
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather",
            "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]}
        }
    }
]
text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True)
```

## Evaluation Results

Tested on a **Tesla T4** (5.56 GB VRAM) via Hugging Face Jobs:

| Category | Result |
|---|---|
| Basic Response | ✅ 1/1 |
| Context Recall | ✅ 1/1 |
| Factual Accuracy | ✅ 1/1 |
| Instruction Following | ✅ 1/1 |
| JSON Output | ✅ 1/1 |
| Multi-turn | ✅ 1/1 |
| Name Recognition | ✅ 1/1 |
| Tool Calling | ✅ 1/1 |
| **Overall** | **✅ 8/8 (100%)** |

**Model load time:** 137s on T4  
**Full eval report:** [`eval/workbench-7b-2026-07-07.json`](https://huggingface.co/Nanthasit/sakthai-context-7b-merged/blob/main/eval/workbench-7b-2026-07-07.json)

## Smaller Variants

| Model | Size | Description |
|---|---|---|
| ⭐ [sakthai-context-1.5b-merged](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) | 1.5B | Balanced size/quality |
| ⭐ [sakthai-context-0.5b-merged](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) | 0.5B | Lightweight for edge/CPU |

## Files

| File | Description |
|---|---|
| `model.safetensors` | Merged BF16 weights (13.8 GB) |
| `config.json` | Model configuration |
| `tokenizer.json` / `tokenizer_config.json` | Qwen2.5 tokenizer with chat template |
| `generation_config.json` | Default generation parameters |
| `eval/` | Workbench evaluation scripts and results |