NexesMess/Llama_3.x_70b_Smarteaz_0.2_NMT

Full fine-tune vs huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

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

1 derivatives checked

• mradermacher/Llama_3.x_70b_Smarteaz_0.2_NMT-GGUF: Quantization

On the Hub · Downloads on Model Pulse