ChaoticNeutrals/Eris_PrimeV4-Vision-7B

Full fine-tune vs ChaoticNeutrals/Eris_PrimeV3.05-Vision-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 128/128, MLP 96/96, Norms 63/65, Embeddings 1/1, lm_head 1/1

1 derivatives checked

• mradermacher/Eris_PrimeV4-Vision-7B-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse