Yuma42/Llama3.1-CrimeSolver-8B

Full fine-tune vs stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/Llama3.1-CrimeSolver-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse