Instructions to use minkdank/LLAMA-JSON-data-extration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minkdank/LLAMA-JSON-data-extration with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="minkdank/LLAMA-JSON-data-extration",
	filename="Llama-3.2-3B-Instruct.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use minkdank/LLAMA-JSON-data-extration with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf minkdank/LLAMA-JSON-data-extration:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf minkdank/LLAMA-JSON-data-extration:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf minkdank/LLAMA-JSON-data-extration:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf minkdank/LLAMA-JSON-data-extration: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 minkdank/LLAMA-JSON-data-extration:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf minkdank/LLAMA-JSON-data-extration: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 minkdank/LLAMA-JSON-data-extration:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf minkdank/LLAMA-JSON-data-extration:Q4_K_M

Use Docker

docker model run hf.co/minkdank/LLAMA-JSON-data-extration:Q4_K_M

LM Studio
Jan
Ollama
How to use minkdank/LLAMA-JSON-data-extration with Ollama:
```
ollama run hf.co/minkdank/LLAMA-JSON-data-extration:Q4_K_M
```

Unsloth Studio

How to use minkdank/LLAMA-JSON-data-extration 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 minkdank/LLAMA-JSON-data-extration 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 minkdank/LLAMA-JSON-data-extration to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for minkdank/LLAMA-JSON-data-extration to start chatting

Docker Model Runner
How to use minkdank/LLAMA-JSON-data-extration with Docker Model Runner:
```
docker model run hf.co/minkdank/LLAMA-JSON-data-extration:Q4_K_M
```

Lemonade

How to use minkdank/LLAMA-JSON-data-extration with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull minkdank/LLAMA-JSON-data-extration:Q4_K_M

Run and chat with the model

lemonade run user.LLAMA-JSON-data-extration-Q4_K_M

List all available models

lemonade list

minkdank commited on Nov 12, 2025

Commit

fac60a8

verified ·

1 Parent(s): e04b50d

Add README

Browse files

Files changed (1) hide show

README.md +15 -4

README.md CHANGED Viewed

@@ -3,7 +3,7 @@ tags:
 - gguf
 - llama.cpp
 - unsloth
 ---
 # LLAMA-JSON-data-extration - GGUF
@@ -15,7 +15,18 @@ This model was finetuned and converted to GGUF format using [Unsloth](https://gi
 - For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
 ## Available Model files:
-- `llama-3.2-3b-instruct.Q8_0.gguf`
-## Ollama
-An Ollama Modelfile is included for easy deployment.

 - gguf
 - llama.cpp
 - unsloth
+- vision-language-model
 ---
 # LLAMA-JSON-data-extration - GGUF
 - For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
 ## Available Model files:
+- `gemma-3-4b-it.Q8_0.gguf`
+- `gemma-3-4b-it.BF16-mmproj.gguf`
+## ⚠️ Ollama Note for Vision Models
+**Important:** Ollama currently does not support separate mmproj files for vision models.
+To create an Ollama model from this vision model:
+1. Place the `Modelfile` in the same directory as the finetuned bf16 merged model
+3. Run: `ollama create model_name -f ./Modelfile`
+   (Replace `model_name` with your desired name)
+This will create a unified bf16 model that Ollama can use.
+## Note
+The model's BOS token behavior was adjusted for GGUF compatibility.