OBLITERATUS/Mistral-7B-v0.3-OBLITERATED

Full fine-tune vs mistralai/Mistral-7B-v0.3. Fine-tune: 92% of the weights changed, across 30 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 90/96, Attention 120/128, lm_head 1/1

2 derivatives checked

• mradermacher/Mistral-7B-v0.3-OBLITERATED-i1-GGUF: Quantization
• mradermacher/Mistral-7B-v0.3-OBLITERATED-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse