Elias

werelax's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

liked 2 Spaces 2 months ago

Runtime error

352

👀

Pixart-α

Running on Zero

583

🖼

OmniGen

Image generator/identifier/reposer

reacted to grimjim's post with 👀 3 months ago

view post

Post

1967

I was reading through an abstract and found myself wondering how much LLM performance is being left on the table due to insufficient curation of training datasets: "Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning" by Kaur, Park, Goyal, Arora.
https://arxiv.org/abs/2408.14774
In particular, the observation that "Introducing low quality answers ("shirkers") in 20% of Instruct-SkillMix examples causes performance to plummet..." had me wondering how many ostensibly good datasets out there are in fact populated with a significant number of "shirkers".

• 
• 
• 7 replies

·

👀

4

4

🚀

3

3

👍

1

1

+

Reply

upvoted a collection 5 months ago

Hermes 3

Collection

The Hermes 3 Series of Models • 10 items • Updated 23 days ago • 100

updated a collection 7 months ago

interesting models

Collection

3 items • Updated May 24, 2024

liked a model 7 months ago

bartowski/LLaMA3-iterative-DPO-final-GGUF

Text Generation • Updated Aug 29, 2024 • 1.14k • 73

updated a collection 7 months ago

interesting models

Collection

3 items • Updated May 24, 2024

liked a model 7 months ago

01-ai/Yi-1.5-34B-Chat

Text Generation • Updated Aug 27, 2024 • 8.98k • • 260

updated a collection 8 months ago

AI Papers

Collection

34 items • Updated May 16, 2024

upvoted 8 papers 8 months ago

Extending Llama-3's Context Ten-Fold Overnight

Paper • 2404.19553 • Published Apr 30, 2024 • 33

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published Apr 30, 2024 • 47

KAN: Kolmogorov-Arnold Networks

Paper • 2404.19756 • Published Apr 30, 2024 • 108

STT: Stateful Tracking with Transformers for Autonomous Driving

Paper • 2405.00236 • Published Apr 30, 2024 • 7

Clover: Regressive Lightweight Speculative Decoding with Sequential Knowledge

Paper • 2405.00263 • Published May 1, 2024 • 14

FLAME: Factuality-Aware Alignment for Large Language Models

Paper • 2405.01525 • Published May 2, 2024 • 24

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

Paper • 2405.00732 • Published Apr 29, 2024 • 118

ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models

Paper • 2405.09220 • Published May 15, 2024 • 24

updated a collection 9 months ago

AI Papers

Collection

34 items • Updated May 16, 2024