MiniMoog/Mergerix-7b-v0.5

Full fine-tune vs automerger/PasticheInex12-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

2 derivatives checked

• mradermacher/Mergerix-7b-v0.5-GGUF: Quantization
• featherless-ai-quants/MiniMoog-Mergerix-7b-v0.5-GGUF: Quantization

On the Hub · Downloads on Model Pulse