GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Nanthasit
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Nanthasit
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Benchmark: sakthai-bench-v2 · 500 samples · run 2026-08-01
Overall (strict): 43.79 · Selection: 43.79 · Arguments: 44.66
| Category | Count | Selection | Arguments | Strict |
|---|---|---|---|---|
| irrelevance_no_tools | 50 | 100.00 | 100.00 | 100.00 |
| irrelevance_tools | 150 | 97.33 | 100.00 | 97.33 |
| parallel | 137 | 0.00 | 0.00 | 0.00 |
| simple | 122 | 4.10 | 4.10 | 4.10 |
| held_out | - | 7.14 | 7.14 | 7.14 |
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:
<tool_call> XML output formatThis section documents the evaluation results for the SakThai Context 1.5B Merged model using standardized benchmarks.
| Benchmark | Metric | Value | Notes |
|---|---|---|---|
| Tool Calling (Reminder) | Success Rate (all trials) | 100% | 3/3 trials produced valid tool calls |
| Tool Calling (Reminder) | JSON Validity | 100% | All outputs were valid JSON format |
| Tool Calling (Reminder) | Correct Answers | 100% | All generated arguments matched expected values |
| Inference Speed (q4_k_m GGUF) | Generation Speed | 5.23 tokens/sec |
Evaluation Details:
For full evaluation details, see the .eval_results/ directory on the Hub.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchmodel = AutoModelForCausalLM.from_pretrained("Nanthasit/sakthai-context-1.5b-merged",torch_dtype=torch.bfloat16,device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-context-1.5b-merged")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").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))
bash
# Pull with Ollamaollama pull sakthai:1.5b# Or download GGUF directlyhuggingface-cli download Nanthasit/sakthai-context-1.5b-merged --include "*.gguf" --local-dir ./# Or run locally with llama.cppwget https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged/resolve/main/sakthai-1.5b-Q4_K_M.gguf./llama-cli -m sakthai-1.5b-Q4_K_M.gguf -p "What's the weather in Tokyo?" -n 128 -t 4
dockerfile
FROM ./sakthai-1.5b-Q4_K_M.ggufPARAMETER temperature 0.3PARAMETER top_p 0.9PARAMETER num_ctx 32768TEMPLATE """{{- range .Messages }}{{ .Role }}\n{{ .Content }}
This model emits structured tool calls as XML. Provide a <tools> block in the system prompt, and it responds with a <tool_call> block instead of plain text when a tool is needed:
text
<tools>{"type": "function", "function": {"name": "get_weather", "description": "Get current weather", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]}}}</tools>
Expected model output when the user asks about weather:
text
<tool_call>{"name": "get_weather", "arguments": {"location": "Tokyo"}}</tool_call>
Note: The
<tools>block is required for reliable function calling — the model was trained on this exact XML format. Omitting it makes the model fall back to answering directly.
| 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) |
| Intermediate size | 8,960 |
| Vocab size | 151,936 |
Config values verified against config.json (2026-07-31).
| 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 (2,003 train + 113 eval) + v7 (2,309 train + 115 eval) + irrelevance-supplement (60 rows) |
| Format | ChatML with tool schema |
Row counts API-verified via datasets-server /size + line count of data/train.jsonl (2026-07-31). Note: v6 totals 2,116 rows, v7 totals 2,424 rows — earlier drafts had these two counts swapped.
| Metric | Result | Status |
|---|---|---|
| Tool calling (get_weather, search_web, calculate, get_time, irrelevance) | 5/5 | ✅ Self-verified — llama.cpp Q4_K_M, temp=0.1 (2026-07-25); not HF-verified |
Tool calling spot-check (set_reminder, 3 seeds) | 3/3 | ✅ Verified — llama.cpp GGUF Q4_K_M, CPU, 2 threads (2026-07-31) |
| sakthai-bench-v2 selection (500 rows, multiset-selection-v2) | 48.2 | ℹ️ Internal — recorded in bench-v2 results/HISTORY.md + family health-check (2026-07-30), not independently re-run |
| Full independent bench-v2 run (arguments + strict metrics) |
The verified 5/5 tool-calling score improved from an earlier 4/5 (bfcl v1) — the merged model now correctly handles search_web. The full multi-trial benchmark run on sakthai-bench-v2 (500 rows, multiset-selection-v2 scorer) remains pending.
set_reminder scenarioA 3-seed single-scenario benchmark landed in the repo's own .eval_results/benchmark-20260731_034419.yaml — llama.cpp GGUF Q4_K_M, CPU, 2 threads, tool_calling_reminder_date prompt. 3/3 trials produced a tool call, valid JSON, and the correct answer (avg 5.23 tok/s):
| Seed | Output tokens | Tool call | Valid JSON | Correct answer |
|---|---|---|---|---|
| 7 | 28 | ✅ | ✅ | ✅ |
| 42 | 28 | ✅ | ✅ | ✅ |
| 1337 | 28 | ✅ | ✅ | ✅ |
This is a single-scenario sanity benchmark (3 seeds), not the full 500-row bench-v2 suite — full-suite results remain pending.
The sakthai-bench-v2 dataset's own results/HISTORY.md (2026-07-30T00:05:03Z, multiset-selection-v2 scorer) records a 48.2% selection accuracy for this model (pre-fix set-subset scorer: 56.6%). Arguments / strict / held-out were not re-scored. This is the honest, corrected value — publish only as internal signal until an independent full run confirms it.
Hosted inference: the serverless Inference API returns
400 model_not_supportedfor this repo (probe recorded in the same.eval_resultsYAML, 2026-07-31). Use the GGUF with llama.cpp/Ollama or the Transformers weights locally — see Quick Start.
| Model | Tool Call Acc. | Arguments Acc. | Context | Merged | GGUF | Notes |
|---|---|---|---|---|---|---|
| SakThai Context 1.5B ⬅ | 5/5 ✅ | pending | 32K | ✅ | ✅ | Self-verified, llama.cpp Q4_K_M |
| Qwen2.5-1.5B-Instruct (base) | N/A | N/A | 32K |
| Task | Tokens/sec | Model config | Hardware |
|---|---|---|---|
Tool-calling set_reminder (avg 3 seeds) | 5.23 | Q4_K_M, temp=0.1 | CPU (2 threads) |
| Full text generation (128 tokens) | ~4.8 | Q4_K_M, temp=0.3, top_p=0.9 | CPU (2 threads) |
| Merging (QLoRA→Full, 1xT4 GPU) | ~12 min | 32 params batch=1 | Free Kaggle T4 |
Key finding: CPU-friendly inference (~5 tok/s) makes this model suitable for edge devices and local-first applications with budget constraints.
| Signal | Value |
|---|---|
| Downloads rank | #1 of 19 Nanthasit models (1,599) |
| Download velocity | #1 of 19 — ~63.0 downloads/day |
| Health score | 97/100 (health-check 2026-07-31 05:22Z) / 85/100 (cron-eval 2026-07-31 09:00Z) |
| Card quality | 88/100 · Repo hygiene 100/100 · Popularity 100 · Momentum 100 (cron-eval) |
| Model age | 25.4 days |
| Likes | 0 — be the first ⭐ |
Sourced from the repo's own .eval_results/cron-eval-sakthai-context-1.5b-merged-2026-07-31-1.yaml and .eval_results/health-context-1.5b-merged-2026-07-31.yaml.
| Stage | Model | Role |
|---|---|---|
| 🔍 Retrieve | Embedding Multilingual | Cross-lingual search |
| 🧠 Reason | Context 1.5B Merged ⬅ | Tool-calling, agentic decisions |
| 🖼️ See | Vision 7B | Image understanding |
| 🎤 Speak | TTS Model |
This card’s verified scores are rerunnable from the published artifact .eval_results/benchmark-20260731_034419.yaml.
Reproduce the 3/3 set_reminder spot-check locally:
huggingface-cli download Nanthasit/sakthai-context-1.5b-merged --include "*.gguf" --local-dir ././llama-cli -m sakthai-1.5b-Q4_K_M.gguf -f prompt.txt --seed 7 --temp 0.1 -n 32 -t 2jq; expected arguments: {"date":"2026-08-01","time":"09:00"}All three published seeds (7, 42, 1337) passed with identical 28-token outputs.
This model is a small (1.5B) tool-calling fine-tune, not a frontier model. Known limitations, stated honestly:
| Limitation | Detail |
|---|---|
| Scale | 1.54B params — limited world knowledge and reasoning depth vs. 7B+ models. Best for structured tool-calling tasks, not open-ended expertise. |
| Tool-calling format | Emits <tool_call> XML. The <tools> block in the system prompt is required — without it the model answers directly and skips tool use. |
| Argument accuracy | Bench-v2 arguments/strict metrics are not independently scored; only selection accuracy (48.2, internal) is recorded. Argument quality may be weaker than selection quality. |
| Verification status | The 5/5 and 3/3 scores are self-run llama.cpp evals, not HF-verified (verified: false in the model-index). Treat as internal signal until an independent full-suite run confirms them. |
If you use this model in your work, please cite the base model and the SakThai fine-tune:
bibtex
@misc{sakthai-context-1.5b-merged,title={SakThai Context 1.5B Merged — Tool-Calling Fine-Tune},author={Beer (beer-sakthai) and the House of Sak},year={2026},month={july},url = {https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged},note={Fine-tuned from Qwen2.5-1.5B-Instruct via QLoRA on the sakthai-combined v6/v7 datasets}}
bibtex
@article{qwen2.5,title={Qwen2.5 Technical Report},author={Qwen Team},journal={arXiv preprint arXiv:2412.15115},year={2024},url={https://arxiv.org/abs/2412.15115}}
| Model | Size | Downloads | Role |
|---|---|---|---|
| ** Context 1.5B Merged | 3.8 GB | 1855 | Flagship tool-calling |
| Context 0.5B Merged | 1.3 GB | 1692 | Lightweight / edge |
| Context 7B Merged | 14.2 GB | 1024 | Full-power reasoning |
| Embedding Multilingual | ~465 MB | 627 | Cross-lingual embeddings |
Live counts from HF API, verified 2026-08-01T00:00:00Z. Full collection
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)
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.
| llama.cpp on CPU, 256-token context |
| Inference Speed (q4_k_m GGUF) | Prompt Processing | 10.9 tokens/sec | Single-pass throughput |
| Context window | 32,768 tokens |
| Precision | BF16 |
| Eval split | 113 (v6) + 115 (v7) held-out examples |
| Hardware | Free T4 GPU (Kaggle / Colab) |
| pending |
| 🔄 Not yet run |
| ✅ |
| ⚠️ limited |
| No tool-calling training |
| Deepseek-Coder-1.5B | N/A | N/A | 4K | ✅ | ✅ | Code-focused, not tool-calling |
| Text-to-speech |
| Full 500-row bench-v2 run (arguments + strict metrics) is pending — only single-scenario spot-checks are complete. |
| Language | Trained on English data. May perform poorly on other languages, including Thai. |
| Hallucination risk | Like all small LLMs, may fabricate tool names, arguments, or facts. Validate tool calls before execution. |
| Serverless inference | The HF Inference API returns 400 model_not_supported for this repo — use the GGUF with llama.cpp/Ollama or the Transformers weights locally. |
| Context length | 32K context; quality degrades and memory grows significantly toward the upper end of the window. |
| Context 7B 128K | ~500 KB | 610 | 128K context scaffold |
| Context 7B Tools | ~500 MB | 489 | 7B tool-calling LoRA |
| Context 1.5B Tools | ~85 MB | 477 | Tool-calling LoRA |
| Context 1.5B Merged v2 | ~2.9 GB | 337 | Improved v2 merged |
| Vision 7B | ~4.4 GB | 315 | Image-to-text |
| Plus 1.5B LoRA | ~85 MB | 306 | Plus adapter |
| Context 0.5B Tools | ~960 MB | 251 | Edge tool-calling |
| TTS Model | ~150 MB | 248 | Text-to-speech |
| Plus 1.5B | ~2.9 GB | 244 | Enhanced instruct |
| Context 1.5B Tools v2 | ~85 MB | 173 | Refined v2 tool-calling LoRA |
| Coder 1.5B | ~1.2 GB | 151 | Code generation |
| Coder Browser | ~2.9 GB | 54 | Browser-agent model |
| Coder Browser GGUF | ~7.1 GB | 35 | Browser GGUF |
| Coder Browser LoRA | ~85 MB | 21 | Browser adapter |
| Plus 1.5B Coder | ~1.2 GB | 0 | Coding variant |