ctlllll / reward_collapse

Related projects: ⓘ

• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs?
  ☆19Updated 3 months ago
• RLHFlow / Directional-Preference-Alignment
  Directional Preference Alignment
  ☆44Updated 3 months ago
• uscnlp-lime / safer-instruct
  This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"
  ☆14Updated 6 months ago
• formll / resolving-scaling-law-discrepancies
  ☆15Updated 2 months ago
• sail-sg / dice
  Official implementation of Bootstrapping Language Models via DPO Implicit Rewards
  ☆33Updated last month
• petezh / OpenD5
  Tasks for describing differences between text distributions.
  ☆15Updated last month
• allenai / easy-to-hard-generalization
  Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"
  ☆44Updated 8 months ago
• GSYfate / knnlm-limits
  Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"
  ☆15Updated 3 weeks ago
• felixzli / synthetic_pretraining
  ☆40Updated 2 years ago
• kyegomez / Reka-Torch
  Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch
  ☆27Updated this week
• XiangLi1999 / AutoBencher
  ☆22Updated 2 months ago
• allenai / sso
  Repository for Skill Set Optimization
  ☆12Updated last month
• VITA-Group / Junk_DNA_Hypothesis
  [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…
  ☆14Updated 3 months ago
• yikangshen / megablocks
  ☆18Updated 3 months ago
• alon-albalak / FLAD
  Few-shot Learning with Auxiliary Data
  ☆26Updated 9 months ago
• janphilippfranken / sami
  Self-Supervised Alignment with Mutual Information
  ☆12Updated 3 months ago
• belindal / LaMPP
  Code for LaMPP: Language Models as Probabilistic Priors for Perception and Action
  ☆35Updated last year
• yale-nlp / refdpo
  ☆13Updated last month
• scalable-model-editing / unified-model-editing
  We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.
  ☆11Updated 3 weeks ago
• gregorbachmann / Next-Token-Failures
  ☆61Updated 6 months ago
• ethz-spylab / superhuman-ai-consistency
  ☆27Updated last year
• ylsung / vl-merging
  PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"
  ☆36Updated 11 months ago
• Linear95 / DSP
  Domain-specific preference (DSP) data and customized RM fine-tuning.
  ☆24Updated 6 months ago
• csinva / tree-prompt
  Tree prompting: easy-to-use scikit-learn interface for improved prompting.
  ☆27Updated 10 months ago
• wzq016 / PINE
  Offcial Repo of Paper "Eliminating Position Bias of Language Models: A Mechanistic Approach""
  ☆10Updated 3 weeks ago
• cognitiveailab / BYTESIZED32
  Byte-sized text games for code generation tasks on virtual environments
  ☆17Updated 2 months ago
• princeton-nlp / WhatICLLearns
  [ACL 2023 Findings] What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning
  ☆21Updated last year
• nverma1 / merging-text-transformers
  Code for "Merging Text Transformers from Different Initializations"
  ☆18Updated last month
• sail-sg / scaling-with-vocab
  📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623
  ☆52Updated 3 weeks ago
• googleinterns / localizing-paragraph-memorization
  ☆14Updated 6 months ago