Results for “quantum-machine-learning”

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Train quantum circuits with automatic differentiation and build hybrid quantum-classical models using PennyLane, including VQE, QAOA, and integration with PyTorch, JAX, and TensorFlow.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends and integrations with HuggingFace Transformers, vLLM, and PEFT/LoRA.

Build, optimize, and execute quantum circuits on IBM Quantum hardware or local simulators using Qiskit, including transpilation, primitives, and algorithm libraries.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Quantize LLMs to 8/4/3/2/1-bit precision without calibration data, using multiple backends and HuggingFace/vLLM integration.

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.

Expert en informatique quantique avancée (Qiskit, Cirq, algorithms, error correction, DZ research)

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Explain and apply core ML/AI concepts — model types, training pipelines, evaluation metrics, and neural architectures.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

KV cache compression for LLM inference — 4.4x compression, 2x context capacity, near-lossless quality. ICLR 2026 paper implementation with vLLM integration.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Design, simulate, and run quantum circuits on Google Quantum AI and partner hardware using Cirq, including noise modeling and characterization experiments.

Benchmark LLM performance across tasks — latency, quality, cost comparison.

Use when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner — including opening the app, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models. Programmatic access to Classification Learner and Regression Learner apps via AppController.

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Design, simulate, and run quantum circuits on Google Quantum AI hardware and other providers using Cirq, including noise modeling and characterization experiments.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

Assist with Colibri: pure-C LLM inference engine for running GLM-5.2 (744B MoE) on consumer machines with ~25 GB RAM. Use when setting up, building, converting models, running inference, configuring expert streaming and caching, optimizing speculative decoding (MTP), GPU integration, and integrating Colibri into production pipelines. Includes build setup, model download & conversion, chat/inference modes, performance tuning, and API integration patterns.

Train quantum circuits like neural networks with automatic differentiation, device-independent programming, and integration with PyTorch or JAX.