CultriX/NeuralTrix-bf16
Full fine-tune vs CultriX/NeuralTrix-7B-dpo. 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/NeuralTrix-bf16-i1-GGUF: Quantization
- mradermacher/NeuralTrix-bf16-GGUF: Same weights, converted
- CultriX/MergeCeption-7B-v3: Full fine-tune
- ChaoticNeutrals/This_is_fine_7B: Full fine-tune