Muhammad2003/Myriad-7B-Slerp

Full fine-tune vs MaziyarPanahi/Calme-7B-Instruct-v0.9. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 33/65, MLP 90/96, Attention 114/128, lm_head 1/1

3 derivatives checked

• mradermacher/Myriad-7B-Slerp-GGUF: Quantization
• featherless-ai-quants/Muhammad2003-Myriad-7B-Slerp-GGUF: Quantization
• automerger/NeuralsynthesisMyriad-7B: Full fine-tune

On the Hub · Downloads on Model Pulse