DevQuasar-6/Deci.DeciLM-6b-instruct-GGUF

LoRA-style vs Deci/DeciLM-6b-instruct. DevQuasar-6/Deci.DeciLM-6b-instruct-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj changed, in 20 of 32 layers; norms, biases and embeddings are untouched.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 20/128, lm_head 0/1

On the Hub · Downloads on Model Pulse