sakthai-context-0.5b-tools/README.md

license, language, library_name, pipeline_tag, base_model, tags, datasets, model-index, inference, widget

license	language	library_name	pipeline_tag	base_model	tags	datasets	model-index	inference	widget
apache-2.0	en	transformers	text-generation	Qwen/Qwen2.5-0.5B-Instruct	agent conversational ollama transformers small-language-model slm tool-use qwen qwen2.5 sakthai house-of-sak tool-calling function-calling merged edge lightweight low-resource raspberry-pi on-device benchmark eval	Nanthasit/sakthai-combined-v7 Nanthasit/sakthai-bench-v2	name results sakthai-context-0.5b-tools task dataset metrics type name text-generation Tool-Calling name type SakThai Bench v2 (500 rows, scorer multiset-selection-v2) Nanthasit/sakthai-bench-v2 type value name verified evidence selection 91.2 Selection Accuracy true .eval_results/sakthai-bench-v2.yaml type value name verified evidence arguments 45.7 Arguments Accuracy true .eval_results/sakthai-bench-v2.yaml type value name verified evidence strict 45.7 Strict Accuracy true .eval_results/sakthai-bench-v2.yaml type value name verified evidence held-out 87.8 Held-Out Tool Accuracy true .eval_results/sakthai-bench-v2.yaml type value name verified evidence degenerate 0 Degenerate Outputs true .eval_results/sakthai-bench-v2.yaml	parameters temperature max_new_tokens top_p 0.01 256 0.9	text example_title What is the weather in Tokyo? Tool-calling text example_title Who wrote Romeo and Juliet? Direct answer text example_title Search the web for latest AI news Search tool

SakThai Context 0.5B Tools

Ultra-light tool-calling agent · Qwen2.5-0.5B fine-tune · runs in ~1 GB RAM

SakThai Context 0.5B Tools is a prompt-masked SFT of Qwen2.5-0.5B-Instruct optimized for browser/tool calling. It achieves 91.2% selection accuracy on SakThai Bench v2, with 0% degenerate outputs in multi-trial evaluation.

Model Description

SakThai Context 0.5B Tools is a prompt-masked supervised fine-tune of Qwen/Qwen2.5-0.5B-Instruct focused on reliable tool/function calling in conversational agents. The model is trained to select the correct tool, generate valid JSON-style arguments, and avoid degenerate outputs. It is optimized for edge deployment and can run on consumer hardware with ~1 GB RAM.

Key points:

• Base: Qwen/Qwen2.5-0.5B-Instruct
• Training: prompt-masked SFT on tool-calling traces from Nanthasit/sakthai-combined-v7
• Primary use: lightweight agents, on-device assistants, Raspberry Pi / edge deployments
• License: Apache-2.0

Quick Start — Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Nanthasit/sakthai-context-0.5b-tools"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather",
            "parameters": {
                "type": "object",
                "properties": {"location": {"type": "string"}},
                "required": ["location"],
            },
        }
    }
]

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What's the weather in Tokyo?"},
]

text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.01, top_p=0.9)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)

Quick Start — llama.cpp / Ollama

# Convert with llama.cpp and run locally
llama-quantize ./sakthai-context-0.5b-tools-f16.gguf ./model-q4_k_m.gguf Q4_K_M
ollama create sakthai-context-0.5b-tools -f Modelfile
ollama run sakthai-context-0.5b-tools

Usage notes

• For tool calling, always use apply_chat_template(..., tools=tools, tokenize=False, add_generation_prompt=True) so the model receives the proper <tools> block.
• If you want stricter outputs, reduce temperature further, e.g. 0.0.
• For CPU-only inference, set device_map="cpu"; GPU/MPS/CPU auto-detection works with device_map="auto".

Architecture & Config

Field	Value
Architecture	Qwen2ForCausalLM
Model type	qwen2
Vocab size	151936
Hidden size	896
Layers	24
Attention heads	14
KV heads	2
Intermediate size	4864
Activation	silu
Max position	32768
Transformers	5.14.1

Benchmarks

Metric	Value	Verified
Selection Accuracy	91.2%	true
Arguments Accuracy	45.7%	true
Strict Accuracy	45.7%	true
Held-Out Tool Accuracy	87.8%	true
Degenerate Outputs	0%	true

Evidence: .eval_results/sakthai-bench-v2.yaml in repo.

Limitations

• 0.5B parameter scale limits reasoning depth; arguments accuracy is lower than selection accuracy.
• Tool schema adherence degrades on nested arguments and long context traces.
• Current weights are merged; if you need the unmerged adapter, use Nanthasit/sakthai-context-0.5b-tools-sft or Nanthasit/sakthai-context-0.5b-tools-sft-v2.

Citation

If you use this model, please cite the SakThai model family and benchmark:

@misc{sakthai2025context05btools,
  title  = {SakThai Context 0.5B Tools},
  author = {Nanthasit},
  year   = {2026},
  url    = {https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools}
}

SakThai Family

Repo	Downloads	Size	Pipeline
Nanthasit/sakthai-context-1.5b-merged	1855	~4.07 GB	text-generation
Nanthasit/sakthai-context-0.5b-merged	1692	~1.39 GB	text-generation
Nanthasit/sakthai-context-7b-merged	1024	~15.23 GB	text-generation
Nanthasit/sakthai-embedding-multilingual	627	~471 MB	sentence-similarity
Nanthasit/sakthai-context-7b-128k	610	—	text-generation
Nanthasit/sakthai-context-7b-tools	489	~20 MB	text-generation
Nanthasit/sakthai-context-1.5b-tools	477	~8.7 MB	text-generation
Nanthasit/sakthai-context-1.5b-merged-v2	337	~3.09 GB	text-generation
Nanthasit/sakthai-vision-7b	315	~4.71 GB	image-text-to-text
Nanthasit/sakthai-plus-1.5b-lora	306	~74 MB	text-generation
Nanthasit/sakthai-context-0.5b-tools	251	~1.0 GB	text-generation
Nanthasit/sakthai-tts-model	248	~143 MB	text-to-speech
Nanthasit/sakthai-plus-1.5b	244	~3.09 GB	text-generation
Nanthasit/sakthai-context-1.5b-tools-v2	173	~74 MB	text-generation
Nanthasit/sakthai-coder-1.5b	151	~1.12 GB	text-generation
Nanthasit/sakthai-coder-browser	54	~3.09 GB	text-generation
Nanthasit/sakthai-coder-browser-gguf	35	~7.11 GB	text-generation
Nanthasit/sakthai-embedding	23	~110 MB	sentence-similarity
Nanthasit/sakthai-coder-browser-lora	21	~74 MB	text-generation

Download counts and sizes were verified from the Hub API at upload time.