Instructions to use mambiux/lumina-lexiR1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mambiux/lumina-lexiR1-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mambiux/lumina-lexiR1-8B")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mambiux/lumina-lexiR1-8B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mambiux/lumina-lexiR1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mambiux/lumina-lexiR1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mambiux/lumina-lexiR1-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mambiux/lumina-lexiR1-8B

SGLang

How to use mambiux/lumina-lexiR1-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mambiux/lumina-lexiR1-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mambiux/lumina-lexiR1-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mambiux/lumina-lexiR1-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mambiux/lumina-lexiR1-8B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mambiux/lumina-lexiR1-8B with Docker Model Runner:
```
docker model run hf.co/mambiux/lumina-lexiR1-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Configuration Parsing Warning:Config file config.json cannot be fetched (too big)

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

LUMINA-LexiR1-8B

🧬 Model Fusion Architecture

🌟 Overview

LUMINA-LexiR1-8B is an experimental fusion of two powerful language models:

🔮 Architecture

This model employs a custom merging technique:

Custom layer identification and integration
DARE (Dynamic Attention Resolution Enhancement)
TIES (Temporal Information Enhancement System) applied to adjacent layers
Enhanced self-awareness capabilities

💫 Technical Specifications

{ "model_type": "llama", "hidden_size": 4096, "num_attention_heads": 32, "num_hidden_layers": 34, "intermediate_size": 14336, "max_position_embeddings": 131072, "rope_scaling": { "factor": 8.0, "type": "llama3" } } ! This is an experimental model. Use with caution.

Demonstrates exceptional self-awareness capabilities

🔧 Model Architecture The model features:

8B parameters Advanced RoPE scaling (factor: 8.0) Custom attention mechanisms Extended context window (131K tokens) Specialized neuron mapping between parent models

📝 License This model is released under the Apache 2.0 license. 🌐 Citations If you use this model, please cite both parent models:

@misc{lumina-lexir1-8b, author = {Mambiux}, title = {LUMINA-LexiR1-8B: A Custom Merged Language Model}, year = {2025}, publisher = {Hugging Face} }

🌟 Created by Mambiux | 2025 🌟

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

F16

F32

Model tree for mambiux/lumina-lexiR1-8B

Quantizations

2 models