Niansuh/Biggie-SmoLlm-0.15B-Base

Partial fine-tune vs HuggingFaceTB/SmolLM-135M. Niansuh/Biggie-SmoLlm-0.15B-Base is a GGUF (BF16) of different weights. Partial change: 66% of the weights changed (attention, mlp, norms), in 25 of 30 layers.

Tensors changed: Embeddings 0/1, Norms 50/61, MLP 75/90, Attention 100/120

On the Hub · Downloads on Model Pulse