Skip to content
View inkybubble's full-sized avatar
0 followers · 9 following

Block or report inkybubble

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. pirate-bunny-lora pirate-bunny-lora Public

    LoRA fine-tune a small LLM to always speak like a pirate captain with a bunny crew. Qwen3-4B on Apple Silicon with MLX.

    Python

  2. agents-03-workflow-comparison agents-03-workflow-comparison Public

    Benchmark harness comparing agentic workflow patterns on latency, cost, and quality

    Python

  3. llm_patterns_openai llm_patterns_openai Public

    Patterns for the responses API (openai) and for iterative validation of toy structured output

    Python

  4. agents-04-agent-loop agents-04-agent-loop Public

    Agent loop implementation using the Anthropic API

    Python

  5. minimoe minimoe Public

    A minimal Mixture of Experts language model built from scratch in PyTorch. Demonstrates sparse routing, load balancing, and MoE mechanics at 20M parameters

    Python

  6. mi_02_vit_attention_patterns mi_02_vit_attention_patterns Public

    How ViT attention patterns change when fine-tuned for galaxy classification

    Python