argilla/zephyr-7b-spin-iter2-v0
Full fine-tune vs argilla/zephyr-7b-spin-iter1-v0. Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- bartowski/zephyr-7b-spin-iter3-v0-GGUF: Full fine-tune
- mradermacher/zephyr-7b-spin-iter2-v0-GGUF: Same weights, converted
- argilla/zephyr-7b-spin-iter3-v0: Full fine-tune