Instructions to use UnluckyOrangutan/thomas-zhu-lean-premise-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 UnluckyOrangutan/thomas-zhu-lean-premise-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 UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16
# Run inference directly in the terminal:
llama cli -hf UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16
# Run inference directly in the terminal:
llama cli -hf UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16

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 UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16

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 UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16

Use Docker

docker model run hf.co/UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16

LM Studio
Jan
Ollama
How to use UnluckyOrangutan/thomas-zhu-lean-premise-gguf with Ollama:
```
ollama run hf.co/UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16
```

Unsloth Studio

How to use UnluckyOrangutan/thomas-zhu-lean-premise-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for UnluckyOrangutan/thomas-zhu-lean-premise-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for UnluckyOrangutan/thomas-zhu-lean-premise-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for UnluckyOrangutan/thomas-zhu-lean-premise-gguf to start chatting

Docker Model Runner
How to use UnluckyOrangutan/thomas-zhu-lean-premise-gguf with Docker Model Runner:
```
docker model run hf.co/UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16
```

Lemonade

How to use UnluckyOrangutan/thomas-zhu-lean-premise-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull UnluckyOrangutan/thomas-zhu-lean-premise-gguf:F16

Run and chat with the model

lemonade run user.thomas-zhu-lean-premise-gguf-F16

List all available models

lemonade list

Atomic Chat

Thomas Zhu Lean Premise GGUF

GGUF conversion of the Lean premise embedding model used by hanwenzhu/lean-premise-server.

Source model: l3lab/all-distilroberta-v1-lr2e-4-bs256-nneg3-ml-ne2
Source revision: v4.30.0
Architecture: RobertaModel
Converted file: thomas-zhu-lean-premise.f16.gguf

Example with joint-server in non-joint premise mode:

server/build/joint-server.exe --host 127.0.0.1 --port 8081 --model D:/hparam_outputs/thomas-zhu-lean-premise.f16.gguf --no-joint --pooling mean --ctx-size 512

Use /version, /cache, and /select for premise retrieval. Autoregressive chat generation is intentionally rejected in --no-joint mode.

Downloads last month: 8

GGUF

Model size

81.5M params

Architecture

bert

Hardware compatibility

16-bit

Model tree for UnluckyOrangutan/thomas-zhu-lean-premise-gguf

Base model

l3lab/all-distilroberta-v1-lr2e-4-bs256-nneg3-ml-ne2

Quantized

(2)

this model