JoPmt/Trismal-7B-Base-v1v2-Ties
Full fine-tune vs unsloth/mistral-7b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Trismal-7B-Base-v1v2-Ties-GGUF: Same weights, converted
- JoPmt/Trismal-7B-Base-v0v3-Ties: Full fine-tune
- JoPmt/Trismal-Obrum-7B-Base-Ties: Full fine-tune