BramVanroy/fietje-2

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

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

3 derivatives checked

• mradermacher/fietje-2-i1-GGUF: Quantization
• mradermacher/fietje-2-GGUF: Same weights, converted
• BramVanroy/fietje-2-instruct: Full fine-tune

On the Hub · Downloads on Model Pulse