Novaciano/qp-3.2-1B

Full fine-tune vs MOHAMEDSANAF2001/llama3.2-1b-merged-2. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64

3 derivatives checked

• mradermacher/qp-1B-i1-GGUF: Quantization
• mradermacher/qp-1B-GGUF: Same weights, converted
• Novaciano/Pyromancer-3.2-1B: Partial fine-tune

On the Hub · Downloads on Model Pulse