rag_knowledge_intensive

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

space-3

SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation

AlpacaFarm

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

Mixture_of_Experts_Explained

MoE 详解，Mixture of Experts Explained by huggingface

Mistral_7B

We introduce Mistral 7B, a 7–billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms the best open 13B model (Llama 2) across all evaluated benchmarks, and the best released 34B model (Llama 1) in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and automated benchmarks. Our models are released under the Apache 2.0 license.

DemoNSF

DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task

dpo

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

test

方法

Speech Model Pre-training

端到端 SLU 预训练

wae2letter++

wae2letter++ 中文对照翻译