QuantFactory/starcoder2-3b-instruct-v0.1-GGUF
Full fine-tune vs bigcode/starcoder2-3b. QuantFactory/starcoder2-3b-instruct-v0.1-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 122/122, MLP 120/120, Attention 240/240