Other skills

Fine-Tuning with TRL

davila7

Align language models with human preferences using reinforcement learning.

Long Context

davila7

Extend transformer context windows for long documents.

MoE Training

davila7

Efficiently train Mixture of Experts models with DeepSpeed.

Causal Interventions with pyvene

davila7

Perform causal interventions on PyTorch models effortlessly.

Knowledge Distillation

davila7

Compress large language models while retaining performance.

Nnsight Remote Interpretability

davila7

Access and manipulate neural network internals seamlessly.

Sparse Autoencoder Training

davila7

Train and analyze Sparse Autoencoders for interpretable features.

Miles RL Training

davila7

Enterprise-grade reinforcement learning for large models.

Mamba Architecture

davila7

Efficient state-space models for long sequences.

Sentence Transformers

davila7

Generate high-quality embeddings for text and images.

T

Task Execution Engine

davila7

Automate implementation tasks from design documents.

Senior Architect

davila7

Design scalable systems with best practices and automation.

AudioCraft Audio Generation

davila7

Generate music and sound effects from text descriptions.

Segment Anything Model

davila7

Effortlessly segment any object in images with zero-shot capabilities.

Model Merging

davila7

Combine fine-tuned models without retraining.

Lambda Labs GPU Cloud

davila7

On-demand GPU instances for ML training and inference.

P

PEFT Fine-Tuning

davila7

Efficiently fine-tune large language models with minimal resources.

Risk Management Specialist

davila7

Streamline ISO 14971 risk management for medical devices.