Results for “bundle-size”
11 skills
More results
orchestra-research quantizing-models-bitsandbytes
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.
10.4k · bundle
tianhao909 quantizing-models-bitsandbytes
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.
1 · bundle
jiachen-t-wang sa-1b-segment-anything-1-billion-masks-dataset-arxiv-sa1b-20
SA-1B: Segment Anything 1 Billion Masks Dataset
6
lucassantana-dev rag
Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking
1 · bundle
qcmuu quantizing-models-bitsandbytes
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.
0 · bundle
lucassantana-dev context-pack
Build a task-aware context bundle (relevant code + applicable standards + related past decisions) via the local RAG index, capped at a token budget. Use at the start of any implementation/refactor/debug task instead of reading files blindly. Replaces "read whole file" with "retrieve the function + callers + rules + prior ADR."
1
theycallmeholla whiteboard
Plan a chunk of work too big for one agent session by putting it on a shared whiteboard — a map of investigation tickets on GitHub Issues — working them until nothing is left to decide, then snapshotting the board into a handoff artifact. Tickets needing nobody are worked back-to-back; the session stops when the human is the blocker. Use only when the user explicitly invokes whiteboard or asks to draw, work, run, or snapshot a whiteboard/map — not for ordinary planning requests.
0 · bundle
nvidia nemo-mbridge-perf-sequence-packing
Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.
2.2k · bundle
shenxingy handoff
End-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.
8 · bundle
dylanckawalec autoresearch-agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
3 · bundle