SableAI-Dev/Hugo-Lumen-1.0

SableAI Lumen

Lumen is a fine-tuned version of Qwen 3.8-27B optimized for code generation and debugging.

Model Details

• —Base Model: Qwen 3.8-27B
• —Format: GGUF (4-bit quantized)
• —Size: 24GB
• —Language: Russian + English

Usage

Using llama-cpp-python

from llama_cpp import Llama

model = Llama( modelpath="SableAI-Hugo-Lumen1.0.gguf", ngpulayers=-1, nctx=4096 )

response = model( "Write a Python function to sort a list", max_tokens=1024 ) print(response["choices"][0]["text"])

Performance

Tested on coding tasks and debugging scenarios. Better than GigaCode on Russian code tasks.

Limitations

• —Primarily trained for programming tasks
• —May struggle with very long contexts
• —Community feedback welcome