ct2

ct-2's activity

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

upvoted a paper 2 days ago

RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

Paper • 2602.05367 • Published 7 days ago • 7

upvoted a paper 3 days ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published 6 days ago • 40

upvoted a paper 7 days ago

POP: Prefill-Only Pruning for Efficient Large Model Inference

Paper • 2602.03295 • Published 9 days ago • 4

liked a Space 24 days ago

Running on Zero

34

PersonaPlex

🌖

34

Persona Plex Demo for the interested

upvoted a paper about 2 months ago

Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in {pm 1, pm i}

Paper • 2512.02901 • Published Dec 2, 2025 • 6

upvoted a paper 2 months ago

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models

Paper • 2511.23319 • Published Nov 28, 2025 • 24

upvoted a collection 3 months ago

Olmo 3

Collection

Artifacts for the Olmo 3 release. • 9 items • Updated Dec 23, 2025 • 163

liked a model 3 months ago

turboderp/MiniMax-M2-exl3

Updated Nov 1, 2025 • 5 • 8

liked a Space 4 months ago

Sleeping

7

Megrez2-3x7B-A3B

👀

7

Megrez2 Chat Demo

liked a model 4 months ago

turboderp/Qwen3-Next-80B-A3B-Thinking-exl3

Updated Nov 1, 2025 • 21 • 7

New activity in inclusionAI/Ring-1T-preview 5 months ago

what is the active parameters of the model??

1

#2 opened 5 months ago by

ct-2

liked a model 5 months ago

stockmark/Stockmark-2-100B-Instruct

Text Generation • 96B • Updated Sep 25, 2025 • 23 • 10

New activity in unsloth/Qwen3-Next-80B-A3B-Instruct-bnb-4bit 5 months ago

Error when using vLLM

➕ 11

5

#2 opened 5 months ago by

sheliak

New activity in meituan-longcat/LongCat-Flash-Chat 5 months ago

Any plan to release 120b and 20-30b level models?

👍 3

11

#5 opened 5 months ago by

Sunny2038

upvoted a paper 5 months ago

Metis: Training Large Language Models with Advanced Low-Bit Quantization

Paper • 2509.00404 • Published Aug 30, 2025 • 7

upvoted an article 5 months ago

view article

Article

The Hacker's Guide to Building an AI Supercluster

• 

Aug 31, 2025

•

7

liked a model 6 months ago

NexaAI/OmniNeural-4B

Any-to-Any • Updated Nov 7, 2025 • 30 • 161

New activity in moonshotai/Kimi-K2-Instruct 7 months ago

is kimi k2 trained with fp8?

7

#30 opened 7 months ago by

ct-2

liked a model 7 months ago

ai21labs/AI21-Jamba-Mini-1.7

52B • Updated 10 days ago • 892 • 41

upvoted a collection 7 months ago

Jamba 1.7

Collection

The AI21 Jamba family of models are hybrid SSM-Transformer foundation models, blending speed, efficient long context processing, and accuracy. • 4 items • Updated Jul 2, 2025 • 12