Felladrin/gguf-internlm2-chat-1_8b

Same weights, converted vs internlm/internlm2-chat-1_8b. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.

Tensors changed: Attention 0/24, Norms 0/49, MLP 0/72, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse