dariprim/yandexgpt-5-lite-finetuned-gguf

Full fine-tune vs yandex/YandexGPT-5-Lite-8B-instruct. dariprim/yandexgpt-5-lite-finetuned-gguf is a GGUF (Q4_K/Q6_K) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 26/65, MLP 96/96, Attention 128/128, lm_head 1/1

On the Hub · Downloads on Model Pulse