Rush Tabesh

soroushtabesh's activity

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

upvoted a collection 7 days ago

GSQ-RCO-GGUF

Collection

Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form • 3 items • Updated 25 days ago • 68

upvoted a paper 3 months ago

GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding

Paper • 2607.27042 • Published Jul 29 • 21

upvoted a collection 5 months ago

GSQ

Collection

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 17 minutes ago • 16

updated a collection 5 months ago

GSQ

Collection

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 17 minutes ago • 16

updated 4 models 5 months ago

ISTA-DASLab/Qwen3-8B-GGUF-GSQ

Text Generation • 8B • Updated May 18 • 403 • 4

ISTA-DASLab/Llama-3.1-70B-Instruct-2Bit-GSQ

Text Generation • 7B • Updated May 18 • 96 • 2

ISTA-DASLab/Qwen3-4B-GGUF-GSQ

Text Generation • 4B • Updated May 18 • 258 • 1

ISTA-DASLab/Llama-3.1-70B-Instruct-3Bit-GSQ

Text Generation • 9B • Updated May 18 • 86 • 1

updated a collection 5 months ago

GSQ

Collection

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 17 minutes ago • 16

authored a paper 5 months ago

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 23

upvoted 2 papers 5 months ago

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 23

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

Paper • 2605.07850 • Published May 8 • 18

updated a model 7 months ago

daslab-testing/Kimi-K2.5-2bit-GSQ

1T • Updated Mar 24 • 23