nicolasembleton/context-1-GGUF
LoRA-style vs chromadb/context-1. nicolasembleton/context-1-GGUF is a GGUF (BF16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 17 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 21/192