Gacrux-R1-Qwen3-1.7B-MoD
> Gacrux-R1-Qwen3-1.7B-MoD is a high-efficiency, multi-domain model fine-tuned on Qwen3-1.7B with traces of Mixture of Domains (MoD). It...
> Gacrux-R1-Qwen3-1.7B-MoD is a high-efficiency, multi-domain model fine-tuned on Qwen3-1.7B with traces of Mixture of Domains (MoD). It...
Fanar-Math-R1-GRPO is a reasoning-optimized language model built on QCRI/Fanar-1-9B-Instruct. This version is fine-tuned using Group Relative Policy Optimization...
!Deca 2 Banner The Deca 2 family of models, now generally availible, is built on cutting-edge architectures like...
LoRA-адаптер для модели YandexGPT-5-Lite-8B-pretrain обученный на миксе из датасетов реализующих r1 (ризонинг) подход. Обученная модель способна имитировать логические...
This model is the distilled version of DeepSeek-R1 on Llama-3.2-3B with R1-Distill-SFT dataset. This model is 4bit quantized!...
Primal-Mini-3B-Exp is based on the Qwen 3B modality architecture, designed to enhance the reasoning capabilities of 3B-parameter models....
Elita-0.1-Distilled-R1-Abliterated is based on the Qwen [ KT ] model, which was distilled by DeepSeek-AI/DeepSeek-R1-Distill-Qwen-7B. It has been...
QWQ R1 [Reasoning] Distill 1.5B CoT is a fine-tuned language model designed for advanced reasoning and instruction-following tasks....
Этот репозиторий содержит исходный код полной точности в формате «безопасных тензоров» для создания GGUF, GPTQ, EXL2, AWQ, HQQ...
Эта модель представляет собой доработанную версию Qwen/Qwen2.5-1.5B-Instruct. Он был обучен с использованием TRL. Желаемый ввод — абзацы неструктурированного...