ucalyptus (Sayantan Das)

upvoted a paper about 3 hours ago

Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate

Paper • 2401.16788 • Published Jan 30 • 1

upvoted a paper 1 day ago

Octopus v4: Graph of language models

Paper • 2404.19296 • Published 3 days ago • 49

upvoted an article 6 days ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

18 days ago

• 93

upvoted a paper 6 days ago

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

Paper • 2309.10400 • Published Sep 19, 2023 • 20

upvoted a paper 8 days ago

Llama 2: Open Foundation and Fine-Tuned Chat Models

Paper • 2307.09288 • Published Jul 18, 2023 • 233

upvoted an article 9 days ago

Article

LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)

By

•

8 days ago

• 31

upvoted a paper 9 days ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published 10 days ago • 225

upvoted 3 articles 13 days ago

Article

AI Apps in a Flash with Gradio's Reload Mode

17 days ago

• 12

Article

Towards Encrypted Large Language Models with FHE

Aug 2, 2023

• 5

Article

Fine-tune Llama 3 with ORPO

By

•

10 days ago

• 150

upvoted a paper 19 days ago

Learning to Route Among Specialized Experts for Zero-Shot Generalization

Paper • 2402.05859 • Published Feb 8 • 4

upvoted a collection 21 days ago

Zephyr ORPO

Collection

Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook • 3 items • Updated 21 days ago • 13

upvoted a collection 22 days ago

SDXL LoRA

Collection

A few SDXL-LoRA models I've trained • 20 items • Updated Jan 22 • 6

upvoted an article 23 days ago

Article

CodeGemma - an official Google release for code LLMs

24 days ago

• 92

upvoted a paper 24 days ago

Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

Paper • 2404.05405 • Published 24 days ago • 4

upvoted a paper 25 days ago

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Paper • 2403.07816 • Published Mar 12 • 37

upvoted 2 papers 28 days ago

Adapting Large Language Models via Reading Comprehension

Paper • 2309.09530 • Published Sep 18, 2023 • 68

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 13

upvoted 2 papers 29 days ago

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published about 1 month ago • 98

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

Paper • 2404.02905 • Published 29 days ago • 58

upvoted a paper 30 days ago

LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model

Paper • 2404.01331 • Published Mar 29 • 22

upvoted 3 papers about 1 month ago

upvoted a collection about 1 month ago

DRAGON Models

Collection

Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ..." the leading foundation base models • 11 items • Updated Feb 3 • 39

upvoted 3 papers about 1 month ago

RAFT: Adapting Language Model to Domain Specific RAG

Paper • 2403.10131 • Published Mar 15 • 58

KTO: Model Alignment as Prospect Theoretic Optimization

Paper • 2402.01306 • Published Feb 2 • 11

Evolutionary Optimization of Model Merging Recipes

Paper • 2403.13187 • Published Mar 19 • 44

upvoted 3 papers about 2 months ago

WebArena: A Realistic Web Environment for Building Autonomous Agents

Paper • 2307.13854 • Published Jul 25, 2023 • 20

IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages

Paper • 2403.01926 • Published Mar 4 • 1

Unifying Vision, Text, and Layout for Universal Document Processing

Paper • 2212.02623 • Published Dec 5, 2022 • 10

upvoted 3 papers 2 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 560

BitNet: Scaling 1-bit Transformers for Large Language Models

Paper • 2310.11453 • Published Oct 17, 2023 • 93

Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Paper • 2402.17177 • Published Feb 27 • 87

upvoted a collection 2 months ago

Data-efficient LLMs

Collection

dataset pruning for advancing the capabilities of LLMs • 21 items • Updated 10 days ago • 1

upvoted 6 papers 2 months ago

Datasets for Large Language Models: A Comprehensive Survey

Paper • 2402.18041 • Published Feb 28 • 2

Unmasking Deepfakes: Masked Autoencoding Spatiotemporal Transformers for Enhanced Video Forgery Detection

Paper • 2306.06881 • Published Jun 12, 2023 • 1

FaceForensics++: Learning to Detect Manipulated Facial Images

Paper • 1901.08971 • Published Jan 25, 2019 • 1

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 5

Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Paper • 2402.13064 • Published Feb 20 • 45

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21 • 104

upvoted 2 collections 2 months ago

Papers about model merging

Collection

referenced in the mergekit repo: https://github.com/cg123/mergekit • 4 items • Updated Feb 13 • 13

Model Merging Papers

Collection

Collection of relevant papers about model merging • 13 items • Updated about 1 month ago • 4

upvoted a paper 2 months ago

Editing Models with Task Arithmetic

Paper • 2212.04089 • Published Dec 8, 2022 • 4

upvoted 2 collections 2 months ago

SLIM Models

Collection

Structured Language Instruction Models (SLIMs) • 17 items • Updated Mar 19 • 22

WebML

Collection

Machine Learning on the Web • 13 items • Updated Feb 7 • 8

upvoted 2 papers 2 months ago

One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation

Paper • 2402.11909 • Published Feb 19 • 1

Chain-of-Thought Reasoning Without Prompting

Paper • 2402.10200 • Published Feb 15 • 89

upvoted 2 collections 3 months ago

🔮 Mixture of Experts

Collection

MoE done using mergekit and LazyMergekit: https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb#scrollTo=d5mYzDo1q96y • 13 items • Updated Mar 22 • 21

⛔️🔦 Provenance, Watermarking & Deepfake Detection

Collection

Technical tools for more control over non-consensual synthetic content • 14 items • Updated about 1 month ago • 35

upvoted 7 papers 3 months ago

Lost in the Middle: How Language Models Use Long Contexts

Paper • 2307.03172 • Published Jul 6, 2023 • 31

How predictable is language model benchmark performance?

Paper • 2401.04757 • Published Jan 9 • 2

Distilling LLMs' Decomposition Abilities into Compact Language Models

Paper • 2402.01812 • Published Feb 2 • 1

Are Emergent Abilities of Large Language Models a Mirage?

Paper • 2304.15004 • Published Apr 28, 2023 • 5

TinyLlama: An Open-Source Small Language Model

Paper • 2401.02385 • Published Jan 4 • 80

Emergent Abilities of Large Language Models

Paper • 2206.07682 • Published Jun 15, 2022 • 3

Fusion-Eval: Integrating Evaluators with LLMs

Paper • 2311.09204 • Published Nov 15, 2023 • 5

upvoted 2 collections 3 months ago

llm-eval

Collection

4 items • Updated Nov 21, 2023 • 1

LLM as a Judge

Collection

Curated resources that support the use of LLMs to serve as automatic evaluators of other LLM outputs. • 14 items • Updated Feb 19 • 14

upvoted a paper 3 months ago

The Critique of Critique

Paper • 2401.04518 • Published Jan 9 • 1

Sayantan Das

AI & ML interests

Organizations

ucalyptus's activity

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)

AI Apps in a Flash with Gradio's Reload Mode

Towards Encrypted Large Language Models with FHE

Fine-tune Llama 3 with ORPO

CodeGemma - an official Google release for code LLMs