watt-ai/watt-tool-70B

Full fine-tune vs meta-llama/Llama-3.3-70B-Instruct. Fine-tune: 97% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 106/161, MLP 237/240, Attention 316/320, lm_head 1/1

3 derivatives checked

• bartowski/watt-ai_watt-tool-70B-GGUF: Quantization
• mradermacher/watt-tool-70B-i1-GGUF: Quantization
• mradermacher/watt-tool-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse