CultriX/MergeCeption-7B-v3

Full fine-tune vs CultriX/NeuralTrix-bf16. 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

4 derivatives checked

• mradermacher/MergeCeption-7B-v3-GGUF: Same weights, converted
• ichigoberry/pandafish-dt-7b: Full fine-tune
• CultriX/MonaCeption-7B-SLERP: Full fine-tune
• CultriX/AlphaCeption-7B-v1: Full fine-tune

On the Hub · Downloads on Model Pulse