ApolloRaines/Mixtral-8x7B-Instruct-v0.1-Parasite

Partial fine-tune vs mistralai/Mixtral-8x7B-Instruct-v0.1. Partial change: 3% of the weights changed (attention, lm_head), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, MLP 0/768, other 0/32, Norms 0/65, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/Mixtral-8x7B-Instruct-v0.1-Parasite-i1-GGUF: Quantization
• mradermacher/Mixtral-8x7B-Instruct-v0.1-Parasite-GGUF: Quantization

On the Hub · Downloads on Model Pulse