Tsunami-th/Tsunami-0.5x-7B-Instruct
Full fine-tune vs Qwen/Qwen2.5-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1
6 derivatives checked
- mradermacher/Tsunami-0.5x-7B-Instruct-i1-GGUF: Quantization
- mradermacher/Tsunami-0.5x-7B-Instruct-GGUF: Same weights, converted
- brgx53/3Blarenegv3-ECE-PRYMMAL-Martial: Full fine-tune
- brgx53/3Blarenegv2-ECE-PRYMMAL-Martial: Full fine-tune
- Marsouuu/general7Bv2-ECE-PRYMMAL-Martial: Full fine-tune
- EnzoDeg40/CybertronTsunami-7B-slerp: Full fine-tune