mradermacher/hubble-1b-100b_toks-perturbed-hf-GGUF

Same weights, converted vs allegrolab/hubble-1b-100b_toks-perturbed-hf. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/33, MLP 0/96, Attention 0/64

On the Hub · Downloads on Model Pulse