Alex Steiner

einsteiner1983's activity

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

upvoted an article 2 months ago

view article

Article

Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

• 

nvidia

•

Mar 19

• 47

New activity in lukealonso/MiniMax-M2.5-NVFP4 4 months ago

KeyError: '110.w1.input_scale' with TRT

2

#3 opened 4 months ago by

guanwenyu1995

upvoted an article 7 months ago

view article

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

• 

QuentinJG

•

Nov 5, 2025

• 64

New activity in galileo-ai/agent-leaderboard 8 months ago

https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8

2

#7 opened 10 months ago by

einsteiner1983

New activity in google/gemma-3-27b-it-qat-q4_0-gguf 10 months ago

Where is the config.json?

➕ 4

1

#17 opened 10 months ago by

einsteiner1983

New activity in moonshotai/Kimi-K2-Instruct 11 months ago

Run 1T-param on A100/H100(80G)x8 using FP4

🚀🔥 5

7

#9 opened 11 months ago by

ghostplant

New activity in nvidia/Llama-3_3-Nemotron-Super-49B-v1 about 1 year ago

How to combine `thinking on/off` prompt with existing system prompt.

2

#8 opened about 1 year ago by

michaelfeil

New activity in microsoft/Phi-3-mini-128k-instruct almost 2 years ago

When input tokens < 4096 but total input+output tokens >4096 the model produces poor output

👍 2

7

#85 opened almost 2 years ago by

einsteiner1983