Instructions to use hkblockchaintechnology/tiny-agent-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use hkblockchaintechnology/tiny-agent-gguf 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 hkblockchaintechnology/tiny-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hkblockchaintechnology/tiny-agent-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hkblockchaintechnology/tiny-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hkblockchaintechnology/tiny-agent-gguf: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 hkblockchaintechnology/tiny-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf hkblockchaintechnology/tiny-agent-gguf: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 hkblockchaintechnology/tiny-agent-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hkblockchaintechnology/tiny-agent-gguf:Q4_K_M

Use Docker

docker model run hf.co/hkblockchaintechnology/tiny-agent-gguf:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use hkblockchaintechnology/tiny-agent-gguf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hkblockchaintechnology/tiny-agent-gguf:Q4_K_M

Ollama
How to use hkblockchaintechnology/tiny-agent-gguf with Ollama:
```
ollama run hf.co/hkblockchaintechnology/tiny-agent-gguf:Q4_K_M
```
Unsloth Desktop

How to use hkblockchaintechnology/tiny-agent-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hkblockchaintechnology/tiny-agent-gguf: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": "hkblockchaintechnology/tiny-agent-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use hkblockchaintechnology/tiny-agent-gguf with Docker Model Runner:
```
docker model run hf.co/hkblockchaintechnology/tiny-agent-gguf:Q4_K_M
```

Lemonade

How to use hkblockchaintechnology/tiny-agent-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hkblockchaintechnology/tiny-agent-gguf:Q4_K_M

Run and chat with the model

lemonade run user.tiny-agent-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use hkblockchaintechnology/tiny-agent-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hkblockchaintechnology/tiny-agent-gguf: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 hkblockchaintechnology/tiny-agent-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hkblockchaintechnology/tiny-agent-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hkblockchaintechnology/tiny-agent-gguf: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 "hkblockchaintechnology/tiny-agent-gguf: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"

hkblockchaintechnology commited on 8 days ago

Commit

c7d45dc

verified ·

1 Parent(s): 9d13dfd

Model card: rebuilt 1.0.0, Microsoft Office-only comparison, final checksums

Browse files

Files changed (2) hide show

DOWNLOAD.md +2 -2
README.md +4 -4

DOWNLOAD.md CHANGED Viewed

@@ -8,8 +8,8 @@ file browser can look empty even when the file is there.
 | What | Link | Size | SHA-256 |
 |---|---|---|---|
-| Installer (recommended) | [TinyAgentSetup-1.0.0.exe](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgentSetup-1.0.0.exe) | 1,345,009,169 bytes | `88e0381472f488c703ff2a1cefa7ff2c93100921315a2730de75b67a1b9e2587` |
-| Portable ZIP | [TinyAgent-1.0.0-portable.zip](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgent-1.0.0-portable.zip) | 1,441,673,458 bytes | `dba144dd060d2d215c95264b10d5c02ce63534ce4eba061c66835248251711fa` |
 More detail, including the source-only package and verification commands:
 [`releases/README.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/releases/README.md).

 | What | Link | Size | SHA-256 |
 |---|---|---|---|
+| Installer (recommended) | [TinyAgentSetup-1.0.0.exe](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgentSetup-1.0.0.exe) | 1,345,010,094 bytes | `b43411af13f8a31dfbd6bef5d3f3ba9e425179de9f5ae293b7102546cfde33fa` |
+| Portable ZIP | [TinyAgent-1.0.0-portable.zip](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgent-1.0.0-portable.zip) | 1,441,679,370 bytes | `eb134a6632483da1c248b2a67c0f928f0aa217d57f7ea29a3ff89801a50bd3b9` |
 More detail, including the source-only package and verification commands:
 [`releases/README.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/releases/README.md).

README.md CHANGED Viewed

@@ -32,11 +32,11 @@ with no GPU, no cloud API and no account.
 It is in the **dataset** repository, not this model repository, under
 `releases/`. The file browser does not preview `.exe` files, so use the direct
 link if you cannot see it. SHA-256:
-`88e0381472f488c703ff2a1cefa7ff2c93100921315a2730de75b67a1b9e2587`.
 The installer is not code-signed; Windows SmartScreen may ask you to choose
 **More info -> Run anyway**. A [portable ZIP (1.44 GB)](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgent-1.0.0-portable.zip)
 is also published, SHA-256
-`dba144dd060d2d215c95264b10d5c02ce63534ce4eba061c66835248251711fa`.
 All files and checksums: [`releases/README.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/releases/README.md).
 This repository supplies the model that installer uses — or that you can point any
@@ -180,7 +180,7 @@ Measured with the real model in the product pipeline:
 | Repeatability harness, reference hardware | **12 of 12** plans produced a usable document (3 runs each of a Word edit, a spreadsheet edit, a deck edit and a new Word table) |
 | Warm plan | **2.5–5 s** typical; slowest measured 27 s (new Word table) |
-The detailed head-to-head, including where Office and WPS win, is in
 [`docs/COMPARISON-REPORT.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/docs/COMPARISON-REPORT.md).
 One measured failure worth publishing, because it is the kind of thing a card
@@ -400,4 +400,4 @@ the same licence.
 * Project source, benchmarks and generated documents: [`hkblockchaintechnology/tiny-agent`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent)
 * Windows installer (1.34 GB, in the dataset repository): [`TinyAgentSetup-1.0.0.exe`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgentSetup-1.0.0.exe)
 * User guide: [`TinyAgent-UserGuide.pdf`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/docs/TinyAgent-UserGuide.pdf)
-* Measured comparison with Microsoft Office, plus the WPS caveat: [`COMPARISON-REPORT.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/docs/COMPARISON-REPORT.md)

 It is in the **dataset** repository, not this model repository, under
 `releases/`. The file browser does not preview `.exe` files, so use the direct
 link if you cannot see it. SHA-256:
+`b43411af13f8a31dfbd6bef5d3f3ba9e425179de9f5ae293b7102546cfde33fa`.
 The installer is not code-signed; Windows SmartScreen may ask you to choose
 **More info -> Run anyway**. A [portable ZIP (1.44 GB)](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgent-1.0.0-portable.zip)
 is also published, SHA-256
+`eb134a6632483da1c248b2a67c0f928f0aa217d57f7ea29a3ff89801a50bd3b9`.
 All files and checksums: [`releases/README.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/releases/README.md).
 This repository supplies the model that installer uses — or that you can point any
 | Repeatability harness, reference hardware | **12 of 12** plans produced a usable document (3 runs each of a Word edit, a spreadsheet edit, a deck edit and a new Word table) |
 | Warm plan | **2.5–5 s** typical; slowest measured 27 s (new Word table) |
+The detailed head-to-head, including where Microsoft Office wins, is in
 [`docs/COMPARISON-REPORT.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/docs/COMPARISON-REPORT.md).
 One measured failure worth publishing, because it is the kind of thing a card
 * Project source, benchmarks and generated documents: [`hkblockchaintechnology/tiny-agent`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent)
 * Windows installer (1.34 GB, in the dataset repository): [`TinyAgentSetup-1.0.0.exe`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/resolve/main/releases/TinyAgentSetup-1.0.0.exe)
 * User guide: [`TinyAgent-UserGuide.pdf`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/docs/TinyAgent-UserGuide.pdf)
+* Measured comparison with Microsoft Office, including where Tiny Agent loses: [`COMPARISON-REPORT.md`](https://huggingface.co/datasets/hkblockchaintechnology/tiny-agent/blob/main/docs/COMPARISON-REPORT.md)