PARD-DeepSeek-R1-Distill-Qwen-1.5B
PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation PARD is a high-performance speculative decoding method that...
PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation PARD is a high-performance speculative decoding method that...
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This...
Zeta 2 is a new version of Zeta that aims to take the next step forward from Zeta...
This model mlx-community/gte-Qwen2-7B-instruct-4bit-DWQ was converted to MLX format from Alibaba-NLP/gte-Qwen2-7B-instruct using mlx-lm version 0.24.0. Модальности:Генерация текста Области применения:Диалог...
The model was presented in the paper R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement...
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This...
WebGen-LM is trained using the Bolt.diy trajectories generated from a subset of the training set of WebGen-Bench (🤗...
RM-R1 is a training framework for Reasoning Reward Model (ReasRM) that judges two candidate answers by first thinking...
RM-R1 is a training framework for Reasoning Reward Model (ReasRM) that judges two candidate answers by first thinking...
ELYZA-Shortcut-1.0-Qwen-32B — не рассуждающая модель, полученная при разработке рассуждающей модели ELYZA-Thinking-1.0-Qwen-32B. На основе Qwen/Qwen2.5-32B-Instruct эта модель была обучена...