lmstudio-community/OlympicCoder-32B-GGUF

Full fine-tune vs open-r1/OlympicCoder-32B. lmstudio-community/OlympicCoder-32B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 1/1, Norms 0/129, MLP 192/192, Attention 256/448, lm_head 1/1

On the Hub · Downloads on Model Pulse