datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
details_flammenai__flammen24-mistral-7Bdetails_flammenai__flammen26-mistral-7Bdetails_flammenai__Mahou-1.1-mistral-7Bdetails_nbeerbower__flammen10-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen10-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen10-mistral-7B 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_nbeerbower__flammen10-mistral-7B.details_nbeerbower__flammen2
Dataset Card for Evaluation run of nbeerbower/flammen2
Dataset automatically created during the evaluation run of model nbeerbower/flammen2 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 pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_nbeerbower__flammen2.details_flammenai__Mahou-1.3-mistral-7Bdetails_flammenai__flammen29-mistral-7Bdetails_nbeerbower__Flammen-Trismegistus-7B
Dataset Card for Evaluation run of nbeerbower/Flammen-Trismegistus-7B
Dataset automatically created during the evaluation run of model nbeerbower/Flammen-Trismegistus-7B 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_nbeerbower__Flammen-Trismegistus-7B.details_nbeerbower__flammen15X-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen15X-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen15X-mistral-7B 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_nbeerbower__flammen15X-mistral-7B.details_nbeerbower__Flammen-Bophades-7B
Dataset Card for Evaluation run of nbeerbower/Flammen-Bophades-7B
Dataset automatically created during the evaluation run of model nbeerbower/Flammen-Bophades-7B 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_nbeerbower__Flammen-Bophades-7B.casual-conversation-DPOSohamGhadge/casual-conversation with rejected responses generated by Phi-3 q4 and poo
details_nbeerbower__flammen3X
Dataset Card for Evaluation run of nbeerbower/flammen3X
Dataset automatically created during the evaluation run of model nbeerbower/flammen3X 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 pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_nbeerbower__flammen3X.lm-eval-results-nbeerbower-Flammen-Bophades-7B-private
Dataset Card for Evaluation run of nbeerbower/Flammen-Bophades-7B
Dataset automatically created during the evaluation run of model nbeerbower/Flammen-Bophades-7B
The dataset is composed of 62 configuration(s), each one corresponding 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" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-nbeerbower-Flammen-Bophades-7B-private.details_nbeerbower__flammen3
Dataset Card for Evaluation run of nbeerbower/flammen3
Dataset automatically created during the evaluation run of model nbeerbower/flammen3 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 pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_nbeerbower__flammen3.details_nbeerbower__flammen15-gutenberg-DPO-v1-7B
Dataset Card for Evaluation run of nbeerbower/flammen15-gutenberg-DPO-v1-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen15-gutenberg-DPO-v1-7B 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_nbeerbower__flammen15-gutenberg-DPO-v1-7B.details_flammenai__flammen27-mistral-7BPhoenix-SFT-v1
Phoenix v1 — Memory Extraction Dataset
Synthetic SFT training data for Phoenix, a small (Qwen2.5-class) model
that reads a window of chat messages between a user and an AI character
("Flame") and emits a structured JSON list of memorable facts the Flame
should remember about the user going forward.
This is the v1 dataset shipped by flammen.ai for
the memory layer that drives long-term continuity in async character
conversations. Released as part of flammen.ai's open-source data… See the full description on the dataset page: https://huggingface.co/datasets/flammenai/Phoenix-SFT-v1.details_flammenai__Mahou-1.0-mistral-7Bflame-kindling-v1
flame-kindling-v1
A small, opinionated SFT dataset for finetuning a 3B-class instruct model into a character designer that emits a strict JSON schema from a free-text seed. Built to replace a general RP model (Mistral-Nemo-12B Mahou finetune) being shoehorned into JSON output for flammen.ai's Create-a-Flame pipeline.
400 (seed → DesignedFlame) pairs distilled from Claude Sonnet 4.5 with tool-forcing, validated against a strict pydantic schema, deduplicated by name and… See the full description on the dataset page: https://huggingface.co/datasets/flammenai/flame-kindling-v1.details_flammenai__flammen20-mistral-7Bdetails_nbeerbower__flammen
Dataset Card for Evaluation run of nbeerbower/flammen
Dataset automatically created during the evaluation run of model nbeerbower/flammen 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 pointing to the latest results.… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_nbeerbower__flammen.details_nbeerbower__flammen5-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen5-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen5-mistral-7B 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_nbeerbower__flammen5-mistral-7B.details_nbeerbower__flammen16-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen16-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen16-mistral-7B 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_nbeerbower__flammen16-mistral-7B.details_flammenai__Mahou-1.0-llama3-8Bdetails_flammenai__flammen18X-mistral-7B
Dataset Card for Evaluation run of flammenai/flammen18X-mistral-7B
Dataset automatically created during the evaluation run of model flammenai/flammen18X-mistral-7B 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_flammenai__flammen18X-mistral-7B.details_flammenai__flammen23-mistral-7Bdetails_nbeerbower__flammen6-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen6-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen6-mistral-7B 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_nbeerbower__flammen6-mistral-7B.details_nbeerbower__flammen12-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen12-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen12-mistral-7B 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_nbeerbower__flammen12-mistral-7B.details_nbeerbower__flammen17-mistral-7B
Dataset Card for Evaluation run of nbeerbower/flammen17-mistral-7B
Dataset automatically created during the evaluation run of model nbeerbower/flammen17-mistral-7B 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_nbeerbower__flammen17-mistral-7B.details_flammenai__Mahou-1.2a-llama3-8B