leeminwaan/gpt-oss-20b-pruned-10.2B-GGUF

Full fine-tune vs AmanPriyanshu/gpt-oss-10.2b-specialized-all-pruned-moe-only-14-experts. leeminwaan/gpt-oss-20b-pruned-10.2B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 0/49, MLP 46/48, Attention 96/192, lm_head 1/1

On the Hub · Downloads on Model Pulse