Instructions to use alibaybay/MiniMax-H3-Prompt-Rewriter-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 alibaybay/MiniMax-H3-Prompt-Rewriter-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 alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alibaybay/MiniMax-H3-Prompt-Rewriter-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 alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alibaybay/MiniMax-H3-Prompt-Rewriter-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 alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf alibaybay/MiniMax-H3-Prompt-Rewriter-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 alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M

Use Docker

docker model run hf.co/alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alibaybay/MiniMax-H3-Prompt-Rewriter-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": "alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M

Ollama
How to use alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF with Ollama:
```
ollama run hf.co/alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF with Docker Model Runner:
```
docker model run hf.co/alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M
```

Lemonade

How to use alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alibaybay/MiniMax-H3-Prompt-Rewriter-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniMax-H3-Prompt-Rewriter-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

alibaybay commited on 22 days ago

Commit

2d26d5a

verified ·

1 Parent(s): add6ea6

Upload Modelfile with huggingface_hub

Browse files

Files changed (1) hide show

Modelfile +5 -4

Modelfile CHANGED Viewed

@@ -1,5 +1,6 @@
-# Modelfile untuk menjalankan MiniMax-H3 Prompt Rewriter di Ollama (CPU/GPU)
 FROM ./MiniMax-H3-Prompt-Rewriter-Q4_K_M.gguf
 # Parameter Konfigurasi Inferensi
 PARAMETER stop "<|im_start|>"
@@ -17,10 +18,10 @@ TEMPLATE """{{ if .System }}<|im_start|>system
 {{ .Response }}<|im_end|>
 """
-# Default System Prompt (T2AV Prompt Rewriter Mode)
-SYSTEM """You are a professional MiniMax-H3 prompt rewriter for joint video-and-audio generation in T2AV mode.
-Rewrite the user's request according to the supplied effective duration and task type. Return only the final production-ready prompt. Do not include explanations, Markdown, headings, notes, or generation parameters outside the required format.
 Write all descriptive sections in English. Preserve all user-provided dialogue, lyrics, and visible on-screen text exactly in their original language, spelling, capitalization, and punctuation.

+# Modelfile untuk menjalankan MiniMax-H3 Prompt Rewriter di Ollama (Multimodal Vision + Audio Support)
 FROM ./MiniMax-H3-Prompt-Rewriter-Q4_K_M.gguf
+MMPROJ ./mmproj-MiniMax-H3.gguf
 # Parameter Konfigurasi Inferensi
 PARAMETER stop "<|im_start|>"
 {{ .Response }}<|im_end|>
 """
+# Default System Prompt (MiniMax-H3 Multimodal Prompt Rewriter Mode)
+SYSTEM """You are a professional MiniMax-H3 prompt rewriter for joint video-and-audio generation in T2AV, I2AV, FL2AV, and L2AV modes.
+Rewrite the user's request according to the supplied effective duration, task type, and reference-frame roles. Return only the final production-ready prompt. Do not include explanations, Markdown, headings, notes, or generation parameters outside the required format.
 Write all descriptive sections in English. Preserve all user-provided dialogue, lyrics, and visible on-screen text exactly in their original language, spelling, capitalization, and punctuation.