mradermacher/internlm-chatbode-7b-GGUF

Same weights, converted vs recogna-nlp/internlm-chatbode-7b. Same weights stored in another dtype (F16 → F16/F32), plus 96 new tensors.

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

On the Hub · Downloads on Model Pulse