-
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Paper • 2306.00978 • Published • 17 -
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Paper • 2210.17323 • Published • 13 -
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
Paper • 2208.07339 • Published • 6 -
QLoRA: Efficient Finetuning of Quantized LLMs
Paper • 2305.14314 • Published • 65
Guilherme Monteiro
guicybercode
AI & ML interests
smol-llms, llm-training, chinese-history, brazilian-history, production-ml, terminal-ui, data-curation, edge-ai
Recent Activity
commentedon a paper about 8 hours ago
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data commentedon a paper about 8 hours ago
Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization commentedon a paper 2 days ago
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM SystemsOrganizations
-
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Paper • 2306.00978 • Published • 17 -
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Paper • 2210.17323 • Published • 13 -
LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
Paper • 2208.07339 • Published • 6 -
QLoRA: Efficient Finetuning of Quantized LLMs
Paper • 2305.14314 • Published • 65
Datasets and an interactive explorer connecting Japan, Iceland, mathematics, technology, philosophy, Asian culture and Christian ethics.
spaces 5
Running on Zero
Agents
nl2bash-pt, explorador da medição de erro de tradução
🚀
200 linhas rotuladas, filtros por fonte e classe
Running on Zero
Agents
Piloto de injeção de prompt, explorador
🚀
Resultados agregados de um piloto pequeno, em CPU
Running
Culture Compass
🚀
Explore random multilingual activity prompts
Running
CORS em servidores de LLM locais
🚀
CORS de llama-server, Ollama e vLLM em config padrão
Running
README
🚀
models 10
guicybercode/Aira-2-portuguese-124M-GGUF
Text Generation • 0.1B • Updated • 201
guicybercode/NBR-1B-Portuguese-MCQ-GGUF
Text Generation • 1B • Updated • 164
guicybercode/Tucano-630m-GGUF
Text Generation • 0.6B • Updated • 179
guicybercode/bee-350m-pt-base-GGUF
Text Generation • 0.3B • Updated • 110
guicybercode/zh-news-gpt-20m
Text Generation • Updated • 55
guicybercode/br-sovereign-llm-research
Text Generation • Updated
guicybercode/br-sovereign-llm-smoke
Text Generation • 150k • Updated • 29
guicybercode/Tucano-630m-mlx-4bit
Text Generation • 0.6B • Updated • 47
guicybercode/NBR-1B-Portuguese-MCQ-mlx-4bit
Text Generation • 1B • Updated • 51
guicybercode/Aira-2-portuguese-124M-mlx-4bit
Text Generation • 0.1B • Updated • 46
datasets 9
guicybercode/nl2bash-pt
Viewer • Updated • 24.7k • 252
guicybercode/llm-injection-pilot
Viewer • Updated • 832 • 252 • 1
guicybercode/japan-math-philosophy-prompts
Viewer • Updated • 24 • 112
guicybercode/iceland-tech-christian-ethics-prompts
Viewer • Updated • 24 • 94
guicybercode/cybercode-bench-ptbr
Viewer • Updated • 200 • 120
guicybercode/cors-servidores-llm-locais
Viewer • Updated • 11 • 113
guicybercode/china-brazil-history-corpus
Viewer • Updated • 15 • 66
guicybercode/china-ai-dataset
Viewer • Updated • 91 • 176
guicybercode/br-sovereign-llm-corpus
Viewer • Updated • 8 • 151