byroneverson/internlm2_5-7b-chat-abliterated

Partial fine-tune vs internlm/internlm2_5-7b-chat. Partial change: 36% of the weights changed (attention, embeddings, mlp), in 32 of 32 layers.

Tensors changed: Attention 32/64, Norms 0/65, MLP 32/96, Embeddings 1/1, lm_head 0/1

2 derivatives checked

• mradermacher/internlm2_5-7b-chat-abliterated-i1-GGUF: Quantization
• mradermacher/internlm2_5-7b-chat-abliterated-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse