fft
Kanimus-26B-A4B-FFT-heretic-i1-GGUFdinov2-base_rice-leaf-disease-augmented_fftKanimus-26B-A4B-FFT-heretic-GGUFLlama-3-8B-Instruct-Portuguese-v0.2-fft-GGUFGemma-4-26B-A4B-Animus-V14.1-FFT-heretic-i1-GGUFsuehyunpark_-_potpourri-8b-inst-fft-induction-bc-trajectory-max1-per-task-tool-token-ggufbarc0_-_llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4-ggufPars-Medical-o1-Llama-FFT-i1-GGUF
Datasets
All datasets matching “fft”details_Dans-DiscountModels__Mistral-7b-FFT-Test3
Dataset Card for Evaluation run of Dans-DiscountModels/Mistral-7b-FFT-Test3
Dataset automatically created during the evaluation run of model Dans-DiscountModels/Mistral-7b-FFT-Test3 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 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_Dans-DiscountModels__Mistral-7b-FFT-Test3.marvis_fft_resultsshotpath-subject-replaced-v2-fft-20260711
ShotPath subject-replaced v2 shuffled FFT data
This folder contains the shuffled JSONL and subject supplement images for rerunning Qwen2.5VL/Qwen3VL full fine-tuning.
{
"seed": 2026071119,
"rows": 3003,
"jsonl": "data/shotpath_stage1_stage2_mixed_subject_replaced_v2_shuffle_fft.jsonl",
"subject_supplement_images": 361,
"added_clean_subject_rows": 361,
"item_dimension_counts": {
"camera_position": 767,
"subject": 649,
"framing": 1097,
"light_exposure":… See the full description on the dataset page: https://huggingface.co/datasets/purefall/shotpath-subject-replaced-v2-fft-20260711.details_Dans-DiscountModels__ShearedLlama-1.3b-FFT-Test1
Dataset Card for Evaluation run of Dans-DiscountModels/ShearedLlama-1.3b-FFT-Test1
Dataset automatically created during the evaluation run of model Dans-DiscountModels/ShearedLlama-1.3b-FFT-Test1 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Dans-DiscountModels__ShearedLlama-1.3b-FFT-Test1.idt5-v4-results-final-fft-s2026-20260911T063507183162Z
final-fft-s2026-20260911T063507183162Z
Run artifacts and per-item predictions.
Phase: final. These are newly generated results, not a reproduction of the legacy TCI tables.
See run_manifest.json, rules.json, generation_protocol.json and checkpoint_hashes.json. Structural scores do not establish semantic or Bloom validity.
Metrics
{
"n": 267,
"rule_version": "structural-proxy-v0.4-grounding-separated",
"parse_success_pct": 88.01498127340824,
"bleu":… See the full description on the dataset page: https://huggingface.co/datasets/Firmansyah-Ibrahim/idt5-v4-results-final-fft-s2026-20260911T063507183162Z.eval_diffusion_fft_real_1_stack_bowls_filtered_fixed
eval_diffusion_fft_real_1_stack_bowls_filtered
Task: "Pick up the lego block."
Type: evaluation (filtered)
Robot: Franka FR3
Cameras: observation.images.primary, observation.images.wrist (video, 256x256) @ 15 FPS
Statistics
Metric
Value
Episodes
10
Total frames
3094
Avg frames/episode
309
FPS
15
Format
LeRobot v3.0
Features
Feature
Type
Shape
observation.images.primary
video
[256, 256, 3]
observation.images.wrist
video
[256… See the full description on the dataset page: https://huggingface.co/datasets/continuallearning/eval_diffusion_fft_real_1_stack_bowls_filtered_fixed.