richardyoung/Mistral-7B-Instruct-v0.2-abliterated-obliteratus

Partial fine-tune vs mistralai/Mistral-7B-Instruct-v0.2. Partial change: 29% of the weights changed (attention, lm_head, mlp), in 9 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 27/96, Attention 36/128, lm_head 1/1

2 derivatives checked

• mradermacher/Mistral-7B-Instruct-v0.2-abliterated-obliteratus-i1-GGUF: Quantization
• mradermacher/Mistral-7B-Instruct-v0.2-abliterated-obliteratus-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse