BramVanroy/fietje-2-chat

Full fine-tune vs BramVanroy/fietje-2-instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 64/66, MLP 128/128, Attention 256/256, lm_head 2/2

2 derivatives checked

• mradermacher/fietje-2-chat-i1-GGUF: Quantization
• mradermacher/fietje-2-chat-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse