Understanding LLMs: A Comprehensive Overview from Training to Inference
Paper
ā¢
2401.02038
ā¢
Published
ā¢
62
LLM Related
š« Glossary https://osanseviero.github.io/hackerllama/blog/posts/hitchhiker_guide/
Note š° Two-stage LLM Fine-tuning with Less Specialization and More Generalization https://arxiv.org/abs/2211.00635
-
Learning To Teach Large Language Models Logical Reasoning
Paper ā¢ 2310.09158 ā¢ Published ā¢ 1 -
ChipNeMo: Domain-Adapted LLMs for Chip Design
Paper ā¢ 2311.00176 ā¢ Published ā¢ 8 -
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Paper ā¢ 2308.09583 ā¢ Published ā¢ 7 -
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Paper ā¢ 2306.08568 ā¢ Published ā¢ 28
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Paper ā¢ 2201.11903 ā¢ Published ā¢ 9Note š„š„š„
-
Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs
Paper ā¢ 2310.13961 ā¢ Published ā¢ 4
In-context Continual Learning Assisted by an External Continual Learner
Paper ā¢ 2412.15563 ā¢ PublishedNote In-context class-incremental learning (CIL): A simple method to apply in-context learning to CIL is to incrementally add few-shot training examples for each new class to the in-context prompt. Query ā”ļø (tag generation) | (summaries of similar tags/classes) | (add summaries as few-shot examples to prompt) | (llm) ā”ļø Predicted class Shorter prompts , fast inference
-
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Paper ā¢ 2307.15337 ā¢ Published ā¢ 36 -
Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference
Paper ā¢ 2303.04673 ā¢ Published -
Magicoder: Source Code Is All You Need
Paper ā¢ 2312.02120 ā¢ Published ā¢ 80 -
Scaling Data-Constrained Language Models
Paper ā¢ 2305.16264 ā¢ Published ā¢ 17 -
Adapting Large Language Models via Reading Comprehension
Paper ā¢ 2309.09530 ā¢ Published ā¢ 77 -
LLM360: Towards Fully Transparent Open-Source LLMs
Paper ā¢ 2312.06550 ā¢ Published ā¢ 57 -
Context Tuning for Retrieval Augmented Generation
Paper ā¢ 2312.05708 ā¢ Published ā¢ 17 -
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Paper ā¢ 2309.12284 ā¢ Published ā¢ 19 -
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Paper ā¢ 2309.11235 ā¢ Published ā¢ 16 -
A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise
Paper ā¢ 2312.12436 ā¢ Published ā¢ 13 -
A Vision Check-up for Language Models
Paper ā¢ 2401.01862 ā¢ Published ā¢ 9 -
WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia
Paper ā¢ 2305.14292 ā¢ Published ā¢ 1 -
Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
Paper ā¢ 2401.12954 ā¢ Published ā¢ 29 -
MM-LLMs: Recent Advances in MultiModal Large Language Models
Paper ā¢ 2401.13601 ā¢ Published ā¢ 45 -
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
Paper ā¢ 2401.14196 ā¢ Published ā¢ 48 -
Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
Paper ā¢ 2401.09967 ā¢ Published ā¢ 1 -
The FinBen: An Holistic Financial Benchmark for Large Language Models
Paper ā¢ 2402.12659 ā¢ Published ā¢ 17 -
Evaluating Very Long-Term Conversational Memory of LLM Agents
Paper ā¢ 2402.17753 ā¢ Published ā¢ 18 -
Design2Code: How Far Are We From Automating Front-End Engineering?
Paper ā¢ 2403.03163 ā¢ Published ā¢ 93 -
RAFT: Adapting Language Model to Domain Specific RAG
Paper ā¢ 2403.10131 ā¢ Published ā¢ 67 -
Large Language Models as Markov Chains
Paper ā¢ 2410.02724 ā¢ Published ā¢ 30