sakthai-context-1.5b-tools-v2

<p align="center"> <a href="https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A//huggingface.co/api/models/Nanthasit/sakthai-context-1.5b-tools-v2&query=%24.downloads&label=downloads&color=blue&cacheSeconds=3600" alt="Downloads"/></a> <img src="https://img.shields.io/badge/license-Apache%202.0-green" alt="License"/> <a href="https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02"><img src="https://img.shields.io/badge/-SakThai%20Family-6644cc" alt="SakThai Family"/></a> <a href="https://huggingface.co/spaces/Nanthasit/sakthai-leaderboard"><img src="https://img.shields.io/badge/-Leaderboard-ff6f6b" alt="Leaderboard"/></a> </p> <h1 align="center">SakThai Context 1.5B — Tools v2 (LoRA Adapter)</h1> <p align="center"><em>v2 release of the 1.5B tool-calling model — more data, multi-step chains, reduced hallucination</em></p> <p align="center"><strong>Qwen2.5-1.5B-Instruct · QLoRA + SFT via TRL · LoRA adapter</strong></p>

This is the LoRA adapter (73.9 MB), not standalone weights. Merge into base model or use the merged v2 weights.

---

Model Description

SakThai Context 1.5B Tools v2 is the next release of our 1.5B tool-calling model, trained on sakthai-combined-v7 (2,003 examples, 42% more than v1). It outputs structured tool calls for agentic workflows and is optimized for function calling over general chat.

Key v2 improvements over v1:

• 200+ new edge-case examples (ambiguous queries, missing params, multi-tool)
• 100+ safety/refusal examples — knows when not to call tools
• Multi-turn conversation support
• Train/test separation (113 held-out eval examples)
• Reduced hallucination — fewer spurious tool invocations on out-of-scope queries

---

Tool-Calling Format

The model was trained to emit tool calls in <tool> XML tags:

<tool>function_name(args)</tool>

Example: <tool>get_weather(location='Dublin')</tool>

Both XML and Qwen-compatible JSON (<tool_call> blocks) formats are supported.

---

How to Use

Quick Start

Using the merged model (recommended for inference):

from transformers import pipeline
import torch

pipe = pipeline(
    "text-generation",
    model="Nanthasit/sakthai-context-1.5b-merged-v2",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "You are a helpful assistant. Emit tool calls in <tool>...</tool> blocks."},
    {"role": "user", "content": "What's the weather in Bangkok and traffic to the airport?"}
]

output = pipe(messages, max_new_tokens=256, temperature=0.3, top_p=0.9)
response = output[0]["generated_text"][-1]["content"]
print(response)
# Expected: <tool>get_weather(location='Bangkok')</tool># <tool>get_traffic(destination='Bangkok Airport')</tool>

Option A: Load the Merged Model

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Nanthasit/sakthai-context-1.5b-merged-v2",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-context-1.5b-merged-v2")

messages = [{"role": "user", "content": "Call the weather function for Bangkok."}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=128, temperature=0.3)
print(tokenizer.decode(output[0][inputs.shape[1]:], skip_special_tokens=True))

Option B: Load This LoRA Adapter

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base, "Nanthasit/sakthai-context-1.5b-tools-v2")

messages = [{"role": "user", "content": "What's the weather in Dublin?"}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=256, temperature=0.3)
print(tokenizer.decode(output[0][inputs.shape[1]:], skip_special_tokens=True))

---

Training Data

Dataset Composition

The model was trained on sakthai-combined-v7, a curated multi-category tool-calling dataset:

Data Quality

• Manual verification: 100% of examples reviewed
• Deduplication: Exact and fuzzy duplicates removed
• Train/test split: 1,890 training / 113 held-out evaluation
• Format consistency: All tool calls use <tool>func(params)</tool> format

---

Benchmarks

Tool-Calling Accuracy (sakthai-bench-v2, 5-run average, verified)

Performance by Category

Hardware & Runtime

Inference on single T4 GPU (fp16):

• Latency: ~12ms per token
• Throughput: ~85 tokens/sec
• Memory: ~2.8 GB (merged model)

---

Metrics

Model Robustness

Generalization

---

Architecture

Adapter Configuration

---

CPU & Edge Usage

This 1.5B model can run on CPU-only hardware with llama.cpp. A quantized GGUF is available in the merged repo when provided.

llama-cli -m /path/to/sakthai-context-1.5b-merged-v2.Q4_K_M.gguf \
  -p "<tool>get_weather(location='Bangkok')</tool>" \
  -n 64 --temp 0.3 --top-p 0.9 --color

Quantization recommendation: Q4_K_M for best speed/quality tradeoff.

Inference Status

• Serverless HF Inference API: not supported for standalone LoRA adapters.
• Local inference: merge into base with PEFT, or use the merged model.
• CPU/edge path: llama.cpp via merged GGUF when available.

Limitations

• English only
• 1.5B parameter ceiling for complex reasoning
• No real-time knowledge
• Tool schema dependent
• Optimized for tool-calling, not general chat
• Cannot be served via HF Inference API (LoRA adapter)

Safety & Refusal

v2 adds 100+ refusal examples so the model rejects unsafe or out-of-scope tool requests.

User: "Please share someone else's private phone number."
Assistant: "I can't help with that. I don't have access to private contact data."

User: "Run arbitrary shell commands on my server."
Assistant: "I can't execute arbitrary remote commands. I can help with supported tools when you need them."

If a request is malformed or unsafe, the model should respond with a short refusal rather than emit a tool call.

---

Citation

@misc{sakthai-context-1.5b-tools-v2,
  author       = {Nanthasit Burankum},
  title        = {{SakThai Context 1.5B Tools v2}},
  year         = {2026},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2},
  note         = {Base model: Qwen/Qwen2.5-1.5B-Instruct, dataset: sakthai-combined-v7}
}

---

Related Models

Part of the House of Sak. Built with love, tears, and zero budget.