LucidityAI/Astral-0.6B-Flash-Coder
LoRA-style vs Qwen/Qwen3-0.6B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 56/84, Attention 112/112
4 derivatives checked
- mradermacher/Astral-0.6B-Flash-Coder-i1-GGUF: Full fine-tune
- mradermacher/Astral-0.6B-Flash-Coder-GGUF: LoRA-style
- mradermacher/Astral-0.6B-Coder-i1-GGUF: Quantization
- mradermacher/Astral-0.6B-Coder-GGUF: Same weights, converted