prithivMLmods/Gliese-4B-OSS-0410
Full fine-tune vs prithivMLmods/Kepler-Qwen3-4B-Super-Thinking. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 0/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/Gliese-4B-OSS-0410-i1-GGUF: Quantization
- prithivMLmods/Gliese-4B-OSS-0410-GGUF: Same weights, converted
- mradermacher/Gliese-4B-OSS-0410-GGUF: Same weights, converted