NexesMess/Llama_3.1_70b_Teatime_V1.01

Full fine-tune vs NobodySpecial/Llama-3.1-70B-Instruct-Lorablated-Creative-Writer. Fine-tune: 97% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 87/161, MLP 240/240, Attention 320/320, lm_head 0/1

1 derivatives checked

• mradermacher/Llama_3.1_70b_Teatime_V1.01-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse