derek-thomas (Derek Thomas)

upvoted an article 4 days ago

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

4 days ago

• 24

upvoted a paper 27 days ago

Towards Retrieval Augmented Generation over Large Video Libraries

Paper • 2406.14938 • Published Jun 21 • 18

upvoted 2 papers 28 days ago

CRAG -- Comprehensive RAG Benchmark

Paper • 2406.04744 • Published Jun 7 • 39

The Prompt Report: A Systematic Survey of Prompting Techniques

Paper • 2406.06608 • Published Jun 6 • 48

upvoted 3 papers about 1 month ago

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack

Paper • 2406.10149 • Published Jun 14 • 47

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

Paper • 2406.04271 • Published Jun 6 • 27

Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models

Paper • 2404.02823 • Published Apr 3 • 2

upvoted an article about 2 months ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 123

upvoted a collection about 2 months ago

Lora Land - 27 High-Quality LoRA Adapters

Collection

27 Fine-tuned LoRA Adapters using Mistral-7B. Try them here: https://predibase.com/lora-land • 27 items • Updated Apr 26 • 3

upvoted a paper about 2 months ago

INDUS: Effective and Efficient Language Models for Scientific Applications

Paper • 2405.10725 • Published May 17 • 30

upvoted a collection about 2 months ago

Embedding Model Datasets

Collection

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 67 items • Updated 19 days ago • 52

upvoted 2 articles about 2 months ago

Article

Benchmarking Text Generation Inference

May 29

• 26

Article

Unlocking Longer Generation with Key-Value Cache Quantization

May 16

• 22

upvoted 3 articles 2 months ago

Article

Hugging Face on AMD Instinct MI300 GPU

May 21

• 10

Article

Build AI on premise with Dell Enterprise Hub

May 21

• 13

Article

From cloud to developers: Hugging Face and Microsoft Deepen Collaboration

May 21

• 8

upvoted 3 papers 2 months ago

vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention

Paper • 2405.04437 • Published May 7 • 3

Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models

Paper • 2405.01535 • Published May 2 • 109

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 81

upvoted 25 articles 2 months ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

May 14

• 172

Article

Hugging Face x LangChain : A new partner package in LangChain

May 14

• 94

Article

License to Call: Introducing Transformers Agents 2.0

May 13

• 102

Article

Subscribe to Enterprise Hub with your AWS Account

May 9

• 6

Article

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

May 9

• 8

Article

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

May 3

• 13

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 60

Article

Improving Prompt Consistency with Structured Generations

Apr 30

• 50

Article

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

Apr 29

• 70

Article

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Apr 19

• 87

Article

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs

Apr 16

• 11

Article

Introducing the Open Arabic LLM Leaderboard

May 14

• 56

Article

Running Privacy-Preserving Inference on Hugging Face Endpoints

Apr 16

• 17

Article

Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Face

Apr 16

• 6

Article

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

Apr 15

• 149

Article

Vision Language Models Explained

Apr 11

• 139

Article

Hugging Face partners with Wiz Research to Improve AI Security

Apr 4

• 11

Article

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Apr 3

• 7

Article

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

Apr 4

• 22

Article

Public Policy at Hugging Face

Apr 8

• 17

Article

Bringing serverless GPU inference to Hugging Face users

Apr 2

• 11

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Mar 22

• 48

Article

Introducing the Chatbot Guardrails Arena

Mar 21

• 4

Article

Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models

Mar 20

• 41

Article

GaLore: Advancing Large Model Training on Consumer-grade Hardware

Mar 20

• 22

upvoted 14 articles 3 months ago

Article

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

Mar 15

• 5

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23

• 28

Article

Synthetic data: save money, time and carbon with open source

Feb 16

• 37

Article

From OpenAI to Open LLMs with Messages API

Feb 8

• 9

Article

NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates

Feb 2

• 2

Article

Constitutional AI with Open LLMs

Feb 1

• 5

Article

Introducing the Enterprise Scenarios Leaderboard: a Leaderboard for Real World Use Cases

Jan 31

• 3

Article

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding

Jan 30

• 4

Article

The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models

Jan 29

• 8

Article

Open-source LLMs as LangChain Agents

Jan 24

• 23

Article

Fine-Tune W2V2-Bert for low-resource ASR with 🤗 Transformers

Jan 19

• 9

Article

Preference Tuning LLMs with Direct Preference Optimization Methods

Jan 18

• 26

Article

A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard

Jan 12

• 6

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 28

upvoted 2 papers 3 months ago

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published Apr 30 • 45

Make Your LLM Fully Utilize the Context

Paper • 2404.16811 • Published Apr 25 • 52

Derek Thomas

AI & ML interests

Articles

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Benchmarking Text Generation Inference

AI Watermarking 101: Tools and Techniques

Organizations

derek-thomas's activity

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Training and Finetuning Embedding Models with Sentence Transformers v3

Benchmarking Text Generation Inference

Unlocking Longer Generation with Key-Value Cache Quantization

Hugging Face on AMD Instinct MI300 GPU

Build AI on premise with Dell Enterprise Hub

From cloud to developers: Hugging Face and Microsoft Deepen Collaboration

PaliGemma – Google's Cutting-Edge Open Vision Language Model

Hugging Face x LangChain : A new partner package in LangChain

License to Call: Introducing Transformers Agents 2.0

Subscribe to Enterprise Hub with your AWS Account

Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

Improving Prompt Consistency with Structured Generations

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs

Introducing the Open Arabic LLM Leaderboard

Running Privacy-Preserving Inference on Hugging Face Endpoints

Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Face

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

Vision Language Models Explained

Hugging Face partners with Wiz Research to Improve AI Security

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

Public Policy at Hugging Face

Bringing serverless GPU inference to Hugging Face users

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

Introducing the Chatbot Guardrails Arena

Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models

GaLore: Advancing Large Model Training on Consumer-grade Hardware

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset

🪆 Introduction to Matryoshka Embedding Models

Synthetic data: save money, time and carbon with open source

From OpenAI to Open LLMs with Messages API

NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates

Constitutional AI with Open LLMs

Introducing the Enterprise Scenarios Leaderboard: a Leaderboard for Real World Use Cases

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding

The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models

Open-source LLMs as LangChain Agents

Fine-Tune W2V2-Bert for low-resource ASR with 🤗 Transformers

Preference Tuning LLMs with Direct Preference Optimization Methods

A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard

Faster fine-tuning using TRL & Unsloth