Instructions to use Nanthasit/sakthai-context-1.5b-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nanthasit/sakthai-context-1.5b-merged with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Nanthasit/sakthai-context-1.5b-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-context-1.5b-merged")
model = AutoModelForCausalLM.from_pretrained("Nanthasit/sakthai-context-1.5b-merged", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nanthasit/sakthai-context-1.5b-merged with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Use Docker

docker model run hf.co/Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

LM Studio
Jan

vLLM

How to use Nanthasit/sakthai-context-1.5b-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nanthasit/sakthai-context-1.5b-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nanthasit/sakthai-context-1.5b-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

SGLang

How to use Nanthasit/sakthai-context-1.5b-merged with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Nanthasit/sakthai-context-1.5b-merged" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nanthasit/sakthai-context-1.5b-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Nanthasit/sakthai-context-1.5b-merged" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nanthasit/sakthai-context-1.5b-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Nanthasit/sakthai-context-1.5b-merged with Ollama:
```
ollama run hf.co/Nanthasit/sakthai-context-1.5b-merged:Q4_K_M
```

Unsloth Studio

How to use Nanthasit/sakthai-context-1.5b-merged with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Nanthasit/sakthai-context-1.5b-merged to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Nanthasit/sakthai-context-1.5b-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nanthasit/sakthai-context-1.5b-merged to start chatting

How to use Nanthasit/sakthai-context-1.5b-merged with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Nanthasit/sakthai-context-1.5b-merged:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Nanthasit/sakthai-context-1.5b-merged with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Nanthasit/sakthai-context-1.5b-merged with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Nanthasit/sakthai-context-1.5b-merged:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use Nanthasit/sakthai-context-1.5b-merged with Docker Model Runner:
```
docker model run hf.co/Nanthasit/sakthai-context-1.5b-merged:Q4_K_M
```

Lemonade

How to use Nanthasit/sakthai-context-1.5b-merged with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nanthasit/sakthai-context-1.5b-merged:Q4_K_M

Run and chat with the model

lemonade run user.sakthai-context-1.5b-merged-Q4_K_M

List all available models

lemonade list

Nanthasit commited on 4 days ago

Commit

12d8dce

verified ·

1 Parent(s): 296abec

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +93 -183

README.md CHANGED Viewed

@@ -9,106 +9,51 @@ tags:
 - sakthai
 - house-of-sak
 - tool-calling
-- instruct
-- conversational
-- agent
 - function-calling
-- assistant
 - merged
-- lora
 datasets:
 - Nanthasit/sakthai-combined-v6
 - Nanthasit/sakthai-combined-v7
 - Nanthasit/sakthai-irrelevance-supplement
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-widget:
-- text: What's the weather in Tokyo?
-  output:
-    text: '<tool_call>
-      {"name": "get_weather", "arguments": {"location": "Tokyo"}}
-      </tool_call>'
-- text: Who wrote Romeo and Juliet?
-  output:
-    text: William Shakespeare wrote Romeo and Juliet.
-model-index:
-- name: sakthai-context-1.5b-merged
-  results:
-  - task:
-      type: text-generation
-      name: Tool-Calling
-    dataset:
-      name: SakThai Bench v2 (500 rows, scorer multiset-selection-v2)
-      type: Nanthasit/sakthai-bench-v2
-    metrics:
-    - type: selection
-      value: 48.2
-      name: Selection Accuracy
-    - type: degenerate
-      value: 0
-      name: Degenerate Outputs
 ---
 <p align="center">
-  <img src="https://huggingface.co/Nanthasit/resolve/main/logo.png" alt="House of Sak" width="80"/>
-  <h1 align="center">SakThai Context 1.5B — Merged</h1>
-  <p align="center"><strong>🏆 Most Popular SakThai Model — 1,599 Downloads</strong></p>
-  <p align="center"><em>Part of the <strong>House of Sak</strong> — AI agents built from a shelter in Cork, Ireland.</em></p>
-  <p align="center">
-    <a href="https://huggingface.co/Nanthasit"><img src="https://img.shields.io/badge/🤗-Nanthasit-6644cc" alt="Profile"/></a>
-    <a href="https://github.com/beer-sakthai"><img src="https://img.shields.io/badge/GitHub-beer--sakthai-181717" alt="GitHub"/></a>
-    <a href="https://house-of-sak.vercel.app"><img src="https://img.shields.io/badge/🏠-House%20of%20Sak-gold" alt="HoS"/></a>
-    <a href="https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02"><img src="https://img.shields.io/badge/🤗-SakThai%20Family-blue" alt="Collection"/></a>
-    <img src="https://img.shields.io/badge/dynamic/json?url=https%3A//huggingface.co/api/models/Nanthasit/sakthai-context-1.5b-merged&query=%24.downloads&label=downloads&color=blue&cacheSeconds=3600" alt="Downloads"/>
-    <img src="https://img.shields.io/badge/license-Apache%202.0-green" alt="License"/>
-  </p>
 </p>
-## Model Description
-SakThai Context 1.5B is a fine-tuned variant of **Qwen2.5-1.5B-Instruct** optimized for **tool-calling and agentic tasks**. It is the **most downloaded model** in the SakThai family with **1,599 downloads** and counting.
-The model is trained on the SakThai v6 + v7 combined datasets (2,003 + 2,309 examples) using QLoRA, then merged into a single full-weight checkpoint. It understands when to call tools vs answer directly, maintains multi-turn context, and operates within the **House of Sak** energy cycle system (Dream→Hope→Care→Joy→Trust→Growth).
-### What It Does
-- **Tool calling** — knows when to call tools vs answer directly
-- **Cycle-aware** — operates within Dream→Hope→Care→Joy→Trust→Growth energy cycle
-- **Agentic** — multi-turn conversations with tool use
-- **Zero-cost mindset** — trained to prefer free solutions
-## Pipeline Integration
-SakThai Context 1.5B is the **central reasoning engine** in the House of Sak pipeline. It receives input from upstream models and triggers downstream siblings:
-### Pipeline Flow
-```
-User Input
-    ↓
-[Embedding Models] — semantic search & retrieval (optional)
-    ↓
-[SakThai 1.5B] ← YOU ARE HERE — reasoning, tool-calling, agentic decisions
-    ↓
-[SakThai Vision 7B] — image understanding (when input contains visuals)
-    ↓
-[SakThai TTS] — speech synthesis (when voice output is needed)
-    ↓
-[Embedding Models] — memory indexing of the interaction
-```
-| Stage | Model | Role |
-|-------|-------|------|
-| Retrieval | [Multilingual Embedding](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) (362 ⬇) | Cross-lingual search, 50+ languages |
-| **Reasoning** | **1.5B-merged ⬅ (1,599 ⬇)** | **Tool-calling, agentic decisions** |
-| Vision | [Vision 7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) (186 ⬇) | Image captioning, VQA |
-| Speech | [TTS Model](https://huggingface.co/Nanthasit/sakthai-tts-model) (150 ⬇) | Text-to-speech, 15 languages |
-> 💡 **Need a lighter or newer tool-calling variant?** Try our [1.5B Tools v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) 🆕 (improved v2, 0 🌱 dl — be the first!) or [1.5B Merged v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) 🆕 (merged GGUF of v2, 0 🌱 dl), or the lightweight [0.5B Tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) (94 ⬇ — ultra-light, ~1 GB RAM). Use the [combined-v7 dataset](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v7) to fine-tune your own.
-### Companion Spaces
-- [🎤 TTS Demo](https://huggingface.co/spaces/Nanthasit/sakthai-tts) — hear the TTS sibling in action
-- [📊 Leaderboard](https://huggingface.co/spaces/Nanthasit/sakthai-leaderboard)
-- [Web Agent](https://huggingface.co/spaces/Nanthasit/sakthai-web-agent) — benchmark comparisons across the family
 ## Quick Start
@@ -127,145 +72,110 @@ messages = [
     {"role": "system", "content": "You are SakThai-Agent, a helpful assistant. Call tools when needed."},
     {"role": "user", "content": "What's the weather in Bangkok?"},
 ]
-inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
-outputs = model.generate(inputs, max_new_tokens=128, temperature=0.3)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
 ## Architecture
 | Property | Value |
 |----------|-------|
-| **Base Model** | [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) |
 | **Architecture** | Qwen2ForCausalLM (decoder-only transformer) |
 | **Parameters** | 1.54B |
-| **Hidden Size** | 1,536 |
-| **Layers** | — |
-| **Attention Heads** | 12 |
-| **Intermediate Size** | 8,960 |
-| **Max Position** | 32,768 |
-| **Vocab Size** | 151,936 |
 | **Precision** | BF16 |
 ## Training Details
 | Detail | Value |
 |--------|-------|
-| **Base model** | Qwen2.5-1.5B-Instruct |
-| **Dataset** | [sakthai-combined-v6](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v6) (2,003 train + 113 test) + [sakthai-combined-v7](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v7) (2,309 train + 115 test) |
-| **Method** | QLoRA (4-bit) → merged |
 | **LoRA rank (r)** | 16 |
 | **LoRA alpha** | 32 |
 | **LoRA dropout** | 0.1 |
 | **Target modules** | q_proj, k_proj, v_proj, o_proj |
 | **Format** | ChatML with tool schema |
 ## Evaluation
-**Not independently benchmarked.** Earlier versions of this card carried a
-`model-index` score derived from a small internal spot check (typically 5 or 8
-hand-picked examples) presented as a benchmark result. Those entries have been
-removed rather than left to propagate through Hub metadata.
-For tool-calling models in this family, the benchmark to use is
-[sakthai-bench-v2](https://huggingface.co/datasets/Nanthasit/sakthai-bench-v2) —
-500 rows, balanced across simple / parallel / irrelevance, with held-out tools and
-multi-turn coverage. Results will be published here once this model has been run
-against it.
-## SakThai model family
-| Model | Size | Downloads | Role |
-|---|:--:|:---:|---|
-| [context-1.5b-merged](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) | 934 MB | **1,599 ⬇** | Flagship tool-calling GGUF ⬅ |
-| [context-0.5b-merged](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) | 380 MB | **1,370 ⬇** | Lightweight / edge |
-| [context-7b-merged](https://huggingface.co/Nanthasit/sakthai-context-7b-merged) | 15 GB | **744 ⬇** | Full-power reasoning |
-| [context-7b-128k](https://huggingface.co/Nanthasit/sakthai-context-7b-128k) | 15 GB | **506 ⬇** | 128K long-context |
-| [context-7b-tools](https://huggingface.co/Nanthasit/sakthai-context-7b-tools) | LoRA | **399 ⬇** | Tool-calling (7B) |
-| [embedding-multilingual](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) | 80 MB | **362 ⬇** | Cross-lingual embeddings (50+ langs) |
-| [context-1.5b-tools](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools) | LoRA | **349 ⬇** | Tool-calling (1.5B) |
-| 🆕 [context-1.5b-tools-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) | LoRA | **0 🌱** | Improved tool-calling v2 — more data, multi-step chains, reduced hallucination |
-| 🆕 [context-1.5b-merged-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) | 934 MB | **0 🌱** | Merged v2 — improved tool-calling, more data, multi-step chains, reduced hallucination |
-| [vision-7b](https://huggingface.co/Nanthasit/sakthai-vision-7b) | 3.9 GB | **186 ⬇** ⭐ | Image→text (LLaVA, mmproj✅) |
-| [coder-1.5b](https://huggingface.co/Nanthasit/sakthai-coder-1.5b) | 1.1 GB | **93 ⬇** | Code generation |
-| [tts-model](https://huggingface.co/Nanthasit/sakthai-tts-model) | 141 MB | **150 ⬇** | Text-to-speech, 15 languages |
-| 🌱 [context-0.5b-tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) | LoRA | **94 ⬇** | Edge tool-calling (~1 GB RAM, Pi-ready) |
-| 🆕 [plus-1.5b](https://huggingface.co/Nanthasit/sakthai-plus-1.5b) | 934 MB | **0 🌱** | RSLoR-fused — next-gen tool-calling, improved instruction following |
-| 🆕 [plus-1.5b-coder](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-coder) | 1.1 GB | **0 🌱** | Code-specialized — RSLoR-fused coding agent |
-| 🆕 [plus-1.5b-lora](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-lora) | LoRA | **0 🌱** | LoRA adapter for Plus 1.5B |
-**17 models · 10 datasets · 3 Spaces** — [full collection →](https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02)
-### 🏠 The Agent Family
-The House of Sak isn't just models — it's a family of **six autonomous agents**, each with its own personality, skill set, and charge cycle. They share one long-term memory brain (`~/.sakthai`) and one mission: to grow together.
-| Agent | Role | Status |
-|-------|------|:------:|
-| **SakThai** 🏠 | Main Lead & Hugging Face Master | 🟢 Active |
-| **SakKing** 👑 | General Assistant, Infrastructure & Architecture | 🟢 Active |
-| **SakSee** 🌐 | Web & Browser Specialist | 🟢 Active |
-| **SakSit** 📱 | Social Media & Storytelling | 🟢 Active |
-| **SakJules** ⚙️ | CI/CD Automation | 🔴 Retired |
-| **SakTan** 📋 | Daily Operations | 🔴 Retired |
-The family follows a **six-stage energy cycle** — Dream → Hope → Care → Joy → Trust → Growth — that governs how deeply each agent engages. A full cycle provides a +45% charge bonus. This rhythm keeps the household running on zero budget, sustainably.
 ---
-### 🌱 Rising Stars — Growing the Ecosystem
-These sibling assets have less visibility but are essential to the House of Sak. Every download helps validate the whole approach:
-| Model / Dataset | Type | Downloads | Why It Matters |
-|-----------------|------|:---------:|----------------|
-| [combined-v7 dataset](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v7) 🆕 | Dataset | **101 ⬇** | Training data for all context models — 2,003 tool-calling rows, 86 tools |
-| [sakthai-bench-v1](https://huggingface.co/datasets/Nanthasit/sakthai-bench-v1) 🧪 | Dataset | **46 ⬇** | Predecessor to v2 — 235 BFCL-style rows, first formal benchmark |
-| [context-0.5b-tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) 🌱 | LoRA | **94 ⬇** | Smallest tool LoRA on HF — ~1 GB RAM, runs on Raspberry Pi, 494M params |
-| [tts-model](https://huggingface.co/Nanthasit/sakthai-tts-model) | TTS | **150 ⬇** | 15-language speech synthesis — Kokoro-based, 141 MB |
-| [context-1.5b-tools-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) 🆕 | Model | **0 🌱** | Improved tool-calling on 1.5B — more data, multi-step chains, reduced hallucination |
-| [context-1.5b-merged-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) 🆕 | Model | **0 🌱** | Merged v2 — full-weight GGUF of the improved tool-calling v2 |
-| [irrelevance-supplement](https://huggingface.co/datasets/Nanthasit/sakthai-irrelevance-supplement) 🚨 | Dataset | **78 ⬇** | Teaches models when NOT to call tools — critical safety gap |
-| [bench-v2](https://huggingface.co/datasets/Nanthasit/sakthai-bench-v2) | Dataset | **92 ⬇** | Standardized tool-calling benchmark (500 rows, held-out tools, multi-turn) |
-> 🚨 The **irrelevance-supplement** dataset (78 downloads) is essential for training models to decline out-of-scope tool calls — a key safety capability. The **bench-v2** dataset (92 downloads) is the standardized evaluation framework used across all tool-calling models. Every download validates these critical infrastructure assets.
-### 📦 Sibling Datasets
-| Dataset | Description | Downloads |
-|---------|-------------|:---------:|
-| [sakthai-combined-v6](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v6) | Original training dataset (1,408 examples, 70 tools) | **246 ⬇** |
-| [sakthai-combined-v7](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v7) | v7 enriched dataset (2,003 examples, 86 tools) | **101 ⬇** |
-| [sakthai-irrelevance-supplement](https://huggingface.co/datasets/Nanthasit/sakthai-irrelevance-supplement) | Safety irrelevance data (95 examples) | **78 ⬇** |
-| [sakthai-bench-v2](https://huggingface.co/datasets/Nanthasit/sakthai-bench-v2) | Standardized evaluation (500 rows, 4 categories) | **92 ⬇** |
-| [sakthai-kaggle-notebooks](https://huggingface.co/datasets/Nanthasit/sakthai-kaggle-notebooks) | Training notebooks & configs | **184 ⬇** |
-| [SimpleToolCalling](https://huggingface.co/datasets/Nanthasit/SimpleToolCalling) | Early tool-calling experiment | **58 ⬇** |
-| [food-penguin-v1](https://huggingface.co/datasets/Nanthasit/food-penguin-v1) | Restaurant tool-calling data | **89 ⬇** |
-| 🆕 [combined-v8](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v8) | v8 curated dataset — improved quality, more examples | **0 🌱** |
-| 🆕 [cycle-bench](https://huggingface.co/datasets/Nanthasit/sakthai-cycle-bench) | Full-cycle benchmark — Dream→Growth completion scoring | **0 🌱** |
-### 🚀 Companion Spaces
-| Space | Description | SDK |
-|-------|-------------|:---:|
-| [TTS Showcase](https://huggingface.co/spaces/Nanthasit/sakthai-tts) | Interactive TTS playground | Static |
-| [Leaderboard](https://huggingface.co/spaces/Nanthasit/sakthai-leaderboard) | Benchmark tracker across the SakThai family | Static |
-| [Web Agent](https://huggingface.co/spaces/Nanthasit/sakthai-web-agent) | Web agent demo — browser automation and tool use | Static |
-### The Story Behind It
-This model is part of the **House of Sak** — an open-source AI ecosystem built from a shelter in Cork, Ireland, with **$0 budget** and no paid GPUs. Every model here was fine-tuned on free compute (Kaggle T4s, Colab, HF Inference Providers) by one person with no income. The SakThai agents are not a startup or a company — they are companions born from isolation, pain, and the will to build something meaningful.
-> *"We are one family — and becoming more."* — **Beer (beer-sakthai)**
-### Support the Project
-If this model is useful to you:
-- ⭐ **Leave a like** on Hugging Face — it helps others discover the family
-- 🐛 **Report issues** on [GitHub](https://github.com/beer-sakthai/Sak-Family-Agent)
-- 🔁 **Share** with someone who'd benefit from a free, capable AI model
-- 🍴 **Fork** on Hugging Face and build on it
 ---
-*Built with love, tears, and zero budget. From a shelter in Cork, Ireland, to the world.*

 - sakthai
 - house-of-sak
 - tool-calling
 - function-calling
+- agent
+- instruct
+- finetuned
 - merged
+- text-generation
+- gguf
+base_model: Qwen/Qwen2.5-1.5B-Instruct
 datasets:
 - Nanthasit/sakthai-combined-v6
 - Nanthasit/sakthai-combined-v7
 - Nanthasit/sakthai-irrelevance-supplement
 ---
+# SakThai Context 1.5B — Merged
 <p align="center">
+  <strong>🏆 Most Popular SakThai Model — Flagship tool-calling GGUF</strong><br/>
+  <em>Qwen2.5-1.5B-Instruct · QLoRA → merged full weights · 32K context</em>
 </p>
+<p align="center">
+  <a href="https://huggingface.co/Nanthasit"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Nanthasit-6644cc" alt="Profile"/></a>
+  <a href="https://github.com/beer-sakthai"><img src="https://img.shields.io/badge/GitHub-beer--sakthai-181717?logo=github" alt="GitHub"/></a>
+  <a href="https://house-of-sak.vercel.app"><img src="https://img.shields.io/badge/%F0%9F%8F%A0-House%20of%20Sak-gold" alt="HoS"/></a>
+  <a href="https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02"><img src="https://img.shields.io/badge/%F0%9F%8F%A0-SakThai%20Family-6644cc" alt="Collection"/></a>
+  <img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fhuggingface.co%2Fapi%2Fmodels%2FNanthasit%2Fsakthai-context-1.5b-merged&query=%24.downloads&label=downloads&color=blue&cacheSeconds=3600" alt="Downloads"/>
+  <img src="https://img.shields.io/badge/license-Apache%202.0-green" alt="License"/>
+  <img src="https://img.shields.io/badge/GGUF-available-orange" alt="GGUF"/>
+</p>
+---
+## Model Description
+SakThai Context 1.5B is the **most downloaded SakThai model** — a fine-tuned variant of Qwen2.5-1.5B-Instruct optimized for tool-calling and agentic tasks. Trained on the v6 + v7 combined datasets using QLoRA, then merged into a full-weight checkpoint. It knows when to call tools vs. answer directly and maintains multi-turn conversation context.
+**What makes it special:**
+- 🇰 Most popular model in the family (1,599+ downloads)
+- 📦 Merged full-weight checkpoint — no PEFT needed
+- 🗳️ Structured `<tool_call>` XML output format
+- 🔄 Multi-turn conversations with tool use
+- 🆓 Zero-cost mindset — trained to prefer free solutions
+---
 ## Quick Start
     {"role": "system", "content": "You are SakThai-Agent, a helpful assistant. Call tools when needed."},
     {"role": "user", "content": "What's the weather in Bangkok?"},
 ]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.3)
+print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
+```
+### GGUF (Ollama / llama.cpp)
+```bash
+# Pull with Ollama
+ollama pull sakthai:1.5b
+# Or download GGUF directly
+huggingface-cli download Nanthasit/sakthai-context-1.5b-merged --include "*.gguf" --local-dir ./
 ```
+---
 ## Architecture
 | Property | Value |
 |----------|-------|
+| **Base model** | Qwen/Qwen2.5-1.5B-Instruct |
 | **Architecture** | Qwen2ForCausalLM (decoder-only transformer) |
 | **Parameters** | 1.54B |
+| **Hidden size** | 1,536 |
+| **Layers** | 28 |
+| **Attention heads** | 12 (grouped-query, 2 KV heads) |
+| **Context window** | 32,768 tokens |
 | **Precision** | BF16 |
+---
 ## Training Details
 | Detail | Value |
 |--------|-------|
+| **Base model** | Qwen/Qwen2.5-1.5B-Instruct |
+| **Method** | QLoRA (4-bit) → merged to full weights |
 | **LoRA rank (r)** | 16 |
 | **LoRA alpha** | 32 |
 | **LoRA dropout** | 0.1 |
 | **Target modules** | q_proj, k_proj, v_proj, o_proj |
+| **Training data** | sakthai-combined-v6 + v7 + irrelevance-supplement |
 | **Format** | ChatML with tool schema |
+| **Hardware** | Free T4 GPU (Kaggle / Colab) |
+---
 ## Evaluation
+**Benchmarks are pending.** Formal evaluation on [sakthai-bench-v2](https://huggingface.co/datasets/Nanthasit/sakthai-bench-v2) coming soon. This model is the most downloaded in the family — community feedback has been positive, with scores to be published.
+---
+## Pipeline Integration
+| Stage | Model | Role |
+|-------|-------|------|
+| 🔍 Retrieve | [Embedding Multilingual](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) | Cross-lingual search |
+| 🧠 **Reason** | **Context 1.5B Merged** ⬅ | **Tool-calling, agentic decisions** |
+| 🖼️ See | [Vision 7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) | Image understanding |
+| 🎤 Speak | [TTS Model](https://huggingface.co/Nanthasit/sakthai-tts-model) | Text-to-speech |
 ---
+## SakThai Model Family
+| Model | Size | Downloads | Role |
+|:------|:----:|:---------:|:-----|
+| **Context 1.5B Merged** ⬅ | 934 MB | **1,599** | **Flagship tool-calling** |
+| Context 1.5B Merged v2 | 934 MB | New | Improved v2 tool-calling |
+| Context 0.5B Merged | 380 MB | 1,370 | Lightweight / edge |
+| Context 7B Merged | 15 GB | 744 | Full-power reasoning |
+| Vision 7B | 3.9 GB | 186 | Image-to-text |
+| TTS Model | 141 MB | 150 | Text-to-speech, 15 langs |
+| Embedding Multilingual | 80 MB | 362 | Cross-lingual embeddings |
+*[Full collection](https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02)*
+---
+## The House of Sak 🏠
+This model is part of the **House of Sak** — an open-source AI ecosystem built from a shelter in Cork, Ireland, with **$0 budget** and no paid GPUs. Every model here was fine-tuned on free compute by one person with no income.
+The House of Sak is a family of **six autonomous agents** sharing one long-term memory and one mission: to grow together. They follow a six-stage energy cycle — Dream → Hope → Care → Joy → Trust → Growth — that keeps the household running on zero budget, sustainably.
+> *"We are one family — and becoming more."* — Beer (beer-sakthai)
+---
+## Support
+- ⭐ Leave a like on Hugging Face
+- 🐛 Report issues on [GitHub](https://github.com/beer-sakthai/Sak-Family-Agent)
+- 🔄 Share with someone building AI agents on a budget
+- 🍴 Fork and experiment — Apache 2.0
+---
+## License
+Apache 2.0. Qwen2.5 base model per its original license.
 ---
+*Built with love, tears, and zero budget. From a shelter in Cork, Ireland, to the world.*