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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Nanthasit/sakthai-coder-1.5b 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-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nanthasit/sakthai-coder-1.5b: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-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Nanthasit/sakthai-coder-1.5b: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-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Nanthasit/sakthai-coder-1.5b: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-coder-1.5b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nanthasit/sakthai-coder-1.5b:Q4_K_M

Use Docker

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

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nanthasit/sakthai-coder-1.5b"
# 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-coder-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

Ollama
How to use Nanthasit/sakthai-coder-1.5b with Ollama:
```
ollama run hf.co/Nanthasit/sakthai-coder-1.5b:Q4_K_M
```
Unsloth Desktop

How to use Nanthasit/sakthai-coder-1.5b 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-coder-1.5b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-coder-1.5b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

lemonade run user.sakthai-coder-1.5b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Nanthasit/sakthai-coder-1.5b 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-coder-1.5b: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-coder-1.5b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Nanthasit/sakthai-coder-1.5b 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-coder-1.5b: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-coder-1.5b: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"

YAML Metadata Error:Invalid Eval Result format in .eval_results/health-coder-1.5b-2026-07-31.yaml

Check out the documentation for more information.

Show details

✖ Invalid input: expected array, received object

sakthai-coder-1.5b / .eval_results /health-coder-1.5b-2026-07-31.yaml

Nanthasit

health check 2026-07-31: repo hygiene cleanup (junk removed), metadata fixes

81668c8 verified 2 months ago

Raw History Blame

3.48 kB

	id: Nanthasit/sakthai-coder-1.5b
	type: model
	checked_at: 2026-07-31T08:20Z
	score: 95
	issues:
	- "CRITICAL repo hygiene (flagged by 4+ sibling health checks since 2026-07-30): 1,569 sibling files / ~167.6 MB of stray dev environment pushed with the model — .venv/ (166,445,681 B, 738 files, full Python 3.14 venv incl. anthropic/anyio/mypy/pytest), .hypothesis/ (134), .ruff_cache/ (41), .pytest_cache/ (8), .curator_backups/ (9 incl. skills.tar.gz), .superpowers/, .claude/, .agents/, .github/ (17 workflows), .githooks/, .usage.json (31 KB), .bundled_manifest, .curator_state, .env.example, .gitignore, .markdownlintignore, .textlintignore, .gitleaks.toml — FIXED"
	- "library_name: transformers declared but repo is GGUF-only (no config.json / tokenizer / model.safetensors / generation_config — verified via tree API) — transformers load would fail; FIXED -> library_name: gguf (matches sibling sakthai-coder-browser-gguf convention)"
	- "README 'Inference via HF API' section showed InferenceClient usage for a repo the serverless Inference API cannot serve (no safetensors weights) — FIXED: section replaced with honest GGUF-only note pointing to local llama.cpp / Ollama"
	- "README Ecosystem Status cited stale 2026-07-30 health check (repo hygiene 40/100, overall 46/100) — FIXED: refreshed to hygiene 100/100, overall ~95/100, new report link"
	- "README Repo Status & Housekeeping said cleanup was 'planned' — FIXED: documents completed cleanup (commit c8e78f1)"
	- ".gitattributes contained stale junk-specific LFS entries (.venv/bin/python, .venv/bin/ruff, .venv/*.so, and gguf/sakthai-coder-q4_k_m.gguf at a path that never existed) — FIXED: rewritten to standard HF LFS patterns + root GGUF entry"
	- "model-index 4 entries all verified:false — honest (base-model references + single-trial internal 5/5), no action needed"
	- "0 likes — no organic engagement yet (family-wide pattern)"
	fixes:
	- "Deleted 1,564 junk files / ~167.6 MB in one atomic commit c8e78f1ad43d1a8e20d943812cb10031831dfc66 (19 paths via CommitOperationDelete); repo now 5 top-level entries"
	- "README frontmatter library_name transformers -> gguf (commit 4bd5c03)"
	- "README: Inference section made honest; Ecosystem Status refreshed; Housekeeping section now documents completed cleanup (same commit)"
	- ".gitattributes rewritten to standard HF LFS patterns only (same commit)"
	- "Uploaded health report .eval_results/health-coder-1.5b-2026-07-31.yaml"
	verification: "16/16 README cross-links 200 (collection, 8 datasets, 3 Spaces, Qwen base, GitHub, house-of-sak, profile); GGUF downloadable — resolve -> 206 with GGUF magic bytes (1,117,320,768 B Q4_K_M); tree after cleanup 5 top-level entries (README 19,495 B, .gitattributes 2,363 B, GGUF, .eval_results/ 11 YAMLs, eval/ 4 JSONs); 3/3 sampled .eval_results YAMLs parse; family table 20 rows — all 19 download counts match live API exactly (self 93); live counts 22 public repos (19 public models + eval_results/bench-v3/sakthai-pipeline non-model), 15 public datasets (8 sibling-table rows all match), 4 Spaces; cardData license apache-2.0 / base_model Qwen/Qwen2.5-Coder-1.5B-Instruct / datasets v6+v7+irrelevance all exist; velocity 93 dl / 6.92 d ~ 13.4 dl/day; last commits 07:58Z audit-fix cron (counts verified consistent, no conflict); frontmatter parses after edit"
	report_url: https://huggingface.co/Nanthasit/sakthai-coder-1.5b/blob/main/.eval_results/health-coder-1.5b-2026-07-31.yaml