Octen/Octen-Embedding-8B
Full fine-tune vs Qwen/Qwen3-Embedding-8B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 145/145, MLP 108/108, Attention 144/144
6 derivatives checked
- groxaxo/octen-embedding-8b-w4a16: Quantization
- ENOSYS/Octen-Embedding-8B-750-v1-GGUF: Quantization
- mradermacher/Octen-Embedding-8B-GGUF: Same weights, converted
- litillabs/octen-law-8b-v1: LoRA-style
- cstr/octen-8b-GGUF: Quantization
- uw-math-ai/MathLeap-Octen-8B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.