mradermacher/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku-GGUF

Same weights, converted vs taoki/Swallow-MS-7b-v0.1-qlora-oasst1-jmultiwoz-dolly-amenokaku. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse