Cerebras REAP
Collection
Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method β’ 30 items β’ Updated β’ 139
Robin Davidsson
RDson
AI & ML interests
Software Engineering & AI/ML.
Recent Activity
new activity 1 day ago
RDson/Qwen3.6-27B-MTP-Q4_K_M-GGUF:ζιζζδΈηζ³ updated a model 5 days ago
RDson/Qwen3.6-27B-MTP-IQ4_KS-GGUF published a model 6 days ago
RDson/Qwen3.6-27B-MTP-IQ4_KS-GGUFOrganizations
None yet
upvoted a collection 7 months ago
upvoted a collection about 1 year ago
upvoted a paper about 1 year ago
upvoted a paper over 1 year ago
upvoted a collection over 1 year ago
upvoted a paper almost 2 years ago
upvoted an article about 2 years ago
Article
Run the strongest open-source LLM model: Llama3 70B with just a single 4GB GPU!
β’
44
upvoted a collection about 2 years ago
upvoted 6
papers over 2 years ago
Mistral 7B
Paper β’ 2310.06825 β’ Published β’ 58
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Paper β’ 2308.13137 β’ Published β’ 20
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Paper β’ 2210.17323 β’ Published β’ 10
LoRA: Low-Rank Adaptation of Large Language Models
Paper β’ 2106.09685 β’ Published β’ 60
AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
Paper β’ 2308.03526 β’ Published β’ 29
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Paper β’ 2308.02151 β’ Published β’ 21