 Mistral-7B-v0.1-flashback-v2 является продолжением процесса предварительного обучения базовой модели Mistral-7B-v0.1, используя 2 251 233 темы форума с шведского...
— Model creator: giux78 — Base model: Mistral 7B v0.1 — Model ispiration Zephyr7Bv.0.1 This repo contains GGUF...
This model was converted to MLX format from [mistralai/Mistral-7B-v0.1](). Refer to the original model card for more details...
The following bitsandbytes quantization config was used during training: — quantmethod: bitsandbytes — loadin8bit: False — loadin4bit: True...
A ~50M-parameter Mamba (selective state-space) causal language model, pretrained from scratch on English Wikipedia. Mamba replaces the attention...
A 25B-parameter base model from the Delphi scaling suite. Trained at 1 × 10²³ FLOPs on 628B tokens...
A small ~110M parameter language model implementing the DeepSeek-V4 architecture from scratch. This is the pretrained base model...
Kona2-12B-Base is a 12-billion parameter base language model optimized for Georgian language understanding and generation. It is built...
We present Tri-7B-Base, a foundation language model that serves as the pre-trained base for our Tri-7B model family....
Эта модель щедро создана и сделана с открытым исходным кодом компанией Astronomer. Astronomer является де-факто компанией Apache Airflow,...
