neopolita/jessi-v0.6-falcon3-7b-instruct

Full fine-tune vs tiiuae/Falcon3-7B-Instruct. Fine-tune: 99% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 84/112, lm_head 1/1

2 derivatives checked

• mradermacher/jessi-v0.6-falcon3-7b-instruct-i1-GGUF: Quantization
• mradermacher/jessi-v0.6-falcon3-7b-instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse