Instructions to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf",
	filename="Q4_K_M/DeepSeek-Prover-V2-671B-Q4_K_M-00001-of-00009.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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 AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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 AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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 AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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 AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M

Use Docker

docker model run hf.co/AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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": "AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M

Ollama
How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf with Ollama:
```
ollama run hf.co/AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M
```

Unsloth Studio

How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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 AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-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 AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf with Docker Model Runner:
```
docker model run hf.co/AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M
```

Lemonade

How to use AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.lumynax-reasoning-deepseek-prover-v2-671b-gguf-Q4_K_M

List all available models

lemonade list

AbteeXAILabs commited on 18 days ago

Commit

992a59c

verified ·

1 Parent(s): d04cbea

docs: publish professional LumynaX model card

Browse files

Files changed (4) hide show

README.md +4 -4
checksums.sha256 +3 -3
docs/lumynax-release-overview.svg +2 -2
docs/lumynax-runtime-flow.svg +2 -2

README.md CHANGED Viewed

@@ -21,12 +21,12 @@ tags:
 - sovereign-ai
 ---
-# Fastest — clone & run
 <!-- lumynax-public-release-card:v4 -->
 <p align="center">
-  <img src="docs/lumynax-release-overview.svg" alt="Fastest — clone &amp; run release overview" width="100%" />
 </p>
 <p align="center">
@@ -95,7 +95,7 @@ ollama run lumynax-reasoning-deepseek-prover-v2-671b-gguf
 | Field | Value |
 | --- | --- |
-| Release | `Fastest — clone & run` |
 | Repository | `AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf` |
 | Mode | `Reasoning-oriented local assistant` |
 | Runtime | `llama.cpp / GGUF` |
@@ -115,7 +115,7 @@ ollama run lumynax-reasoning-deepseek-prover-v2-671b-gguf
 ## Runtime Path
 <p align="center">
-  <img src="docs/lumynax-runtime-flow.svg" alt="Fastest — clone &amp; run runtime flow" width="100%" />
 </p>
 ## Capability Profile

 - sovereign-ai
 ---
+# LumynaX Reasoning DeepSeek-Prover V2 671B GGUF
 <!-- lumynax-public-release-card:v4 -->
 <p align="center">
+  <img src="docs/lumynax-release-overview.svg" alt="LumynaX Reasoning DeepSeek-Prover V2 671B GGUF release overview" width="100%" />
 </p>
 <p align="center">
 | Field | Value |
 | --- | --- |
+| Release | `LumynaX Reasoning DeepSeek-Prover V2 671B GGUF` |
 | Repository | `AbteeXAILab/lumynax-reasoning-deepseek-prover-v2-671b-gguf` |
 | Mode | `Reasoning-oriented local assistant` |
 | Runtime | `llama.cpp / GGUF` |
 ## Runtime Path
 <p align="center">
+  <img src="docs/lumynax-runtime-flow.svg" alt="LumynaX Reasoning DeepSeek-Prover V2 671B GGUF runtime flow" width="100%" />
 </p>
 ## Capability Profile

checksums.sha256 CHANGED Viewed

@@ -4,6 +4,6 @@ d0b4f9120ba026c00fa23cb84b4e1620a2e6436592e58155a5151653179572c0  VERSION.txt
 72551608f384dc6f9f00a99044ba37003ea65392b6a9dd6c3bb546d8cabb2c43  quickstart.py
 c7b622002047c0e145bd52317fa1f7915299ec4fe7642969bccbe405ccd3510f  release_export_manifest.json
 44fc2c3474d1cc9ef66f42dfc3fcc4aa571eae4bf7720fae3569a7451f7e4a3f  requirements.txt
-9f18c63e73ff4f842a046b299bc9c4144845dc76634efa68834b5b82aec2554f  README.md
-2b3dc7514206b2a77bb8db336a6a4efbaf5322860f2b74034e69b5edba514052  docs/lumynax-release-overview.svg
-f84ac44a11e07ab343c65f547ef29b347390273dc79ae8543e8855dc51031cb5  docs/lumynax-runtime-flow.svg

 72551608f384dc6f9f00a99044ba37003ea65392b6a9dd6c3bb546d8cabb2c43  quickstart.py
 c7b622002047c0e145bd52317fa1f7915299ec4fe7642969bccbe405ccd3510f  release_export_manifest.json
 44fc2c3474d1cc9ef66f42dfc3fcc4aa571eae4bf7720fae3569a7451f7e4a3f  requirements.txt
+f40a2096848417d0cd7076c8fc8d52778f125355d451da64f13a9a43a854fc2a  README.md
+5e9191124287370e73c35a874e5f6b0b4f98978089379720382cc149a58090e6  docs/lumynax-release-overview.svg
+208335f800d44165c591c8362ea594ddbe86166ecdc1280100b72c3b6a0e3d8b  docs/lumynax-runtime-flow.svg

docs/lumynax-release-overview.svg CHANGED Viewed

docs/lumynax-runtime-flow.svg CHANGED Viewed