DebateLabKIT/Llama-3.3-Argunaut-1-70B-SPIN

Partial fine-tune vs DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT. Partial change: 31% of the weights changed (attention, lm_head, mlp), in 71 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 72/240, Attention 96/320, lm_head 1/1

2 derivatives checked

• mradermacher/Llama-3.3-Argunaut-1-70B-SPIN-i1-GGUF: Quantization
• mradermacher/Llama-3.3-Argunaut-1-70B-SPIN-GGUF: Quantization

On the Hub · Downloads on Model Pulse