Youssef Amrani

youssefam's activity

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

liked a model about 8 hours ago

anthonymikinka/gpt2_coreml_kv_cache_try1

Text Generation • Updated Dec 18, 2024 • 7

upvoted 2 papers about 8 hours ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 27 days ago • 423

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 6 days ago • 157

liked 3 datasets 3 days ago

open-llm-leaderboard-old/details_xformAI__facebook-opt-125m-qcqa-ub-6-best-for-KV-cache

Updated Jan 23, 2024 • 213 • 4

Nathan-Maine/dgx-spark-kv-cache-benchmark

Preview • Updated May 31 • 78 • 4

makora-ai/speculative-decoding-dataset

Viewer • Updated 13 days ago • 1.93M • 29 • 4

liked 2 models 3 days ago

xformAI/opt-6.7b-ub-16-qcqa-best-for-KV-cache

Updated Jan 24, 2024 • 4

position-specialist-speculative-decoding/Speed-E3-Llama3.1-8B-Instruct-vllm

0.9B • Updated Jan 28 • 11 • 3

upvoted a paper 3 days ago

Harness-Zero: Harness Distillation via Agent-as-Harness

Paper • 2609.24974 • Published 7 days ago • 37

upvoted a paper 5 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 11 days ago • 185

liked a model 6 days ago

KVCache-ai/Qwen3-30BA3B-GGUF

31B • Updated Apr 29, 2025 • 40 • 6

upvoted 2 papers 6 days ago

Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches

Paper • 2609.17652 • Published 13 days ago • 8

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Paper • 2609.19134 • Published 12 days ago • 101

upvoted a paper 7 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 21 days ago • 374

liked a dataset 8 days ago

spiritbuun/turboquant-tcq-kv-cache

Updated Apr 6 • 79 • 13

liked 2 models 8 days ago

position-specialist-speculative-decoding/llama3-8b-instruct-poss3

Updated Aug 29, 2025 • 10 • 2

KVCache-ai/Kimi-K2-Instruct-GGUF

1T • Updated Jul 12, 2025 • 20 • 25

upvoted 2 papers 8 days ago

How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus

Paper • 2609.15504 • Published 14 days ago • 37

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

Paper • 2609.13285 • Published 20 days ago • 81