Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
HINT-lab 's Collections
RelayLLM
PosS-Speculative-Decoding
CrossWordBench
Self-Calibration
Reward-Calibration
VLM

PosS-Speculative-Decoding

updated Dec 15, 2025

This collection contains models of the paper "PosS:Position Specialist Generates Better Draft for Speculative Decoding"

Upvote
2

  • HINT-lab/PosS3-E3-Llama3.1-8B-Instruct

    Updated Dec 15, 2025 • 1

  • HINT-lab/PosS3-Llama3-8B-Instruct

    Updated Dec 15, 2025 • 4

  • HINT-lab/PosS3-Llama2-13B-Chat

    Updated Dec 15, 2025

  • HINT-lab/PosS2-Llama3-8B-Instruct

    Updated Dec 15, 2025 • 1

  • HINT-lab/PosS1-Llama3-8B-Instruct

    Updated Dec 15, 2025 • 1

  • HINT-lab/PosS2-Llama2-13B-Chat

    Updated Dec 15, 2025

  • HINT-lab/PosS1-Llama2-13B-Chat

    Updated Dec 15, 2025 • 3

  • HINT-lab/EAGLE-Llama3-8B-Instruct-Reproduce

    Updated Dec 15, 2025

  • HINT-lab/HASS-Llama3-8B-Instruct-Reproduce

    Updated Dec 15, 2025

  • POSS: Position Specialist Generates Better Draft for Speculative Decoding

    Paper • 2506.03566 • Published Jun 4, 2025 • 6
Upvote
2
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs