lora-sft
Datasets
All datasets matching “lora-sft”KoHRM-Text-1.4B-sft-lora-data
KoHRM-Text-1.4B SFT and LoRA Prepared Data
This dataset repo stores curated KoHRM SFT/LoRA subsets in the same tokenized
HRM-Text V1Dataset format used by training. It is intended for quick behavior
alignment experiments after KoHRM pretraining.
Model repo:
https://huggingface.co/LLM-OS-Models/KoHRM-Text-1.4B
Code repo:
https://github.com/LLM-OS-Models/KoHRM-text
Format
Each folder is a prepared V1Dataset:
<dataset-name>/
metadata.json
tokenizer_info.json… See the full description on the dataset page: https://huggingface.co/datasets/LLM-OS-Models/KoHRM-Text-1.4B-sft-lora-data.clean-gsm8k-aug-gpt2-0.1b-lora-think-sft-ar-clean-gsm8k-aug
clean-gsm8k-aug-gpt2-0.1b-lora-think-sft-ar-clean-gsm8k-aug
Ten generated think-sft-ar responses per question from cs-giung/gpt2-0.1b-lora-think-sft-ar-clean-gsm8k-aug (revision step-300000), generated on 2026-08-07.
Schema
Field
Type
Meaning
question
str
Source question from cs-giung/clean-gsm8k-aug
steps
list[list[str]]
The 10 responses, each split into reasoning steps
answer
list[str]
The 10 per-response answer blocks
Every record has… See the full description on the dataset page: https://huggingface.co/datasets/cs-giung/clean-gsm8k-aug-gpt2-0.1b-lora-think-sft-ar-clean-gsm8k-aug.amdpilot-lora-sft-dataset
AMDPilot LoRA SFT Dataset
SFT training data for fine-tuning LLMs on AMD GPU debugging, optimization, and kernel engineering tasks. Each example is a multi-turn conversation in OpenAI messages format with tool-use annotations.
Usage
from datasets import load_dataset
# Load a specific version
ds = load_dataset("JinnP/amdpilot-lora-sft-dataset", "v5_2")
# Load a specific view
ds = load_dataset("JinnP/amdpilot-lora-sft-dataset", "v5_2_chunks")
# Available configs: v4, v5… See the full description on the dataset page: https://huggingface.co/datasets/JinnP/amdpilot-lora-sft-dataset.details_Mikivis__gpt2-large-lora-sft1
Dataset Card for Evaluation run of Mikivis/gpt2-large-lora-sft1
Dataset Summary
Dataset automatically created during the evaluation run of model Mikivis/gpt2-large-lora-sft1 on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Mikivis__gpt2-large-lora-sft1.details_lole25__phi-2-sft-lora-ultrachat
Dataset Card for Evaluation run of lole25/phi-2-sft-lora-ultrachat
Dataset automatically created during the evaluation run of model lole25/phi-2-sft-lora-ultrachat on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_lole25__phi-2-sft-lora-ultrachat.details_eren23__finetune_test_qwen15-1-8b-sft-lora
Dataset Card for Evaluation run of eren23/finetune_test_qwen15-1-8b-sft-lora
Dataset automatically created during the evaluation run of model eren23/finetune_test_qwen15-1-8b-sft-lora on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_eren23__finetune_test_qwen15-1-8b-sft-lora.