yandex/YandexGPT-5-Lite-8B-instruct
Full fine-tune vs yandex/YandexGPT-5-Lite-8B-pretrain. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 31/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/YandexGPT-5-Lite-8B-instruct-i1-GGUF: Quantization
- mradermacher/YandexGPT-5-Lite-8B-instruct-GGUF: Same weights, converted
- LevLv/YandexGPT-5-Lite-8B-Thinking.gguf: Full fine-tune
- dariprim/yandexgpt-5-lite-finetuned-gguf: Full fine-tune
3 other repos hold byte-for-byte identical weight files.