datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
dit-loras-interpreting
andyx10/dit-loras-interpreting
Experimenting with interpreting write vectors over 100 hidden-topic model organisms fromdiff-interpretation-tuning/loras
implementation
We use 'self_attn.o_proj andmlp.down_proj` for write vectors: two per block across 36 blocks, with a total of 72 write vectors per organism.
Jacobian Lens from Neuronpedia
neuronpedia/jacobian-lens
(qwen3-4b/jlens/Salesforce-wikitext/Qwen3-4B_jacobian_lens.pt)
layout
test100/… See the full description on the dataset page: https://huggingface.co/datasets/andyx10/dit-loras-interpreting.w2t-llm-arc-easy-lora
W2T Llm Arc Easy Lora
This repository contains artifacts for the W2T paper:
Paper: W2T: LoRA Weights Already Know What They Can Do
Repo: Weight2Token
Summary
ARC-Easy LoRA checkpoints and prepared metadata used for performance prediction.
Source Status
Storage location: local
Verification status: confirmed
Files
See manifest.json for the exact local or remote source paths used to prepare this release.
Citation… See the full description on the dataset page: https://huggingface.co/datasets/Xiaolong-Han/w2t-llm-arc-easy-lora.benchmark-finetune-lora-v1
Odyn benchmark: LoRA fine-tuning peak VRAM (V1)
Curated benchmark rows for validating GPU memory estimators during LoRA fine-tuning. Each row pairs a published or measured expected peak VRAM with inputs to a math engine (model size, context length, batch, LoRA rank, precision, parallelism) plus optional VRAM breakdown and provenance.
This dataset is not Alpaca-style training JSONL. It is evaluation ground truth for placement / scheduler memory models (Odyn Smart Digester math… See the full description on the dataset page: https://huggingface.co/datasets/odyn-network/benchmark-finetune-lora-v1.lora-hyperparameter-benchmark-v1
Odyn benchmark: LoRA fine-tuning hyperparameter configs (V1)
Curated benchmark of real, cited LoRA and QLoRA fine-tuning configurations for validating a hyperparameter advisor. Each row is a published or measured supervised (SFT) LoRA config with its hyperparameters (learning rate, LoRA rank/alpha/dropout, epochs, batch, sequence length, gradient checkpointing), the dataset it trained on, and per-field provenance.
Schema
Column
Type
Description
id… See the full description on the dataset page: https://huggingface.co/datasets/odyn-network/lora-hyperparameter-benchmark-v1.clip-lora-submissionlora-bp-safety-benchmarkversion https://git-lfs.github.com/spec/v1
oid sha256:7606d91a20699cd5918eeffa95f318781fccfdd705297ddadbf390ea587860e6
size 3781
LoRaNetworkSensorsReadings