mradermacher/salamandra-2B-instruct-smoltalk-GGUF
Partial fine-tune vs sebcif/salamandra-2B-instruct-smoltalk. mradermacher/salamandra-2B-instruct-smoltalk-GGUF is a GGUF (F16) of different weights. Partial change: 87% of the weights changed (attention, lm_head, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1