Octen/Octen-Embedding-4B
Full fine-tune vs Qwen/Qwen3-Embedding-4B. 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
4 derivatives checked
- ENOSYS/Octen-Embedding-4B-750-v1-GGUF: Quantization
- cstr/octen-4b-GGUF: Quantization
- mradermacher/Octen-Embedding-4B-GGUF: Same weights, converted
- mlx-community/Octen-Embedding-4B-MLX-4bit: Quantization