Small models often struggle with consistency, identity confusion, or producing nonsensical wordplay. In this version, we have addressed these core issues:
We tested the model against rigorous academic benchmarks. Here is what these numbers mean for such a compact model:
In its weight class (0.5B), this model is a true champion, especially in hard sciences and logical consistency.
1from transformers import pipeline
2
3# Initialize the pipeline
4pipe = pipeline("text-generation", model="muverqqw/Noir-Lightning", device_map="auto")
5
6# Chat-template based request
7messages = [
8 {"role": "system", "content": "You are Noir, a helpful AI assistant."},
9 {"role": "user", "content": "Explain simply: why is the sky blue?"}
10]
11
12# Generation
13outputs = pipe(messages, max_new_tokens=150, do_sample=True, temperature=0.7)
14print(outputs[0]['generated_text'][-1]['content'])
-
Architecture: Transformers-based Causal Decoder (Qwen 2.5)
-
Training Data: Fine-tuned on a curated blend of logical reasoning, high-quality dialogue, and mathematical datasets.
-
Format: Available in float16. GGUF/EXL2 versions coming soon.
-
Context Length: Supports up to 32k tokens (optimal performance within 4k-8k).
-
Creator: IceL1ghtning
-
Release Year: 2025
-
Base Architecture: Qwen 2.5
-
License: Apache 2.0 (Commercial use permitted)
