datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
qfs-smollm2-135m-wikitext2-native-v1
HF workflow d3dc69602aeb981f06bd9f4c726937f9
A root fidelity dataset in hidden form, produced by engines/tools/hf_capture.py from malaiwah/SmolLM2-135M-QFS-native-bf16.
The cut
the final hidden state handed to lm_head -- after the text model's final norm and immediately before the head matmul -- captured as the head module's input via torch.nn.Module.register_forward_pre_hook; replay applies the head ONLY (no final norm at replay time: the capture already sits… See the full description on the dataset page: https://huggingface.co/datasets/malaiwah/qfs-smollm2-135m-wikitext2-native-v1.qfs-smollm2-135m-wikitext2-gptq-g32-v1
HF workflow 32c6ab05b0ceab1cecdceda838846388
A quant fidelity dataset in hidden form, produced by engines/tools/hf_capture.py from malaiwah/SmolLM2-135M-QFS-gptq-int4-g32.
The cut
the final hidden state handed to lm_head -- after the text model's final norm and immediately before the head matmul -- captured as the head module's input via torch.nn.Module.register_forward_pre_hook; replay applies the head ONLY (no final norm at replay time: the capture already sits… See the full description on the dataset page: https://huggingface.co/datasets/malaiwah/qfs-smollm2-135m-wikitext2-gptq-g32-v1.qfs-smollm2-135m-wikitext2-gptq-g64-v1
HF workflow 73f0a12a901c7368794a3a886f55b675
A quant fidelity dataset in hidden form, produced by engines/tools/hf_capture.py from malaiwah/SmolLM2-135M-QFS-gptq-int4-g64.
The cut
the final hidden state handed to lm_head -- after the text model's final norm and immediately before the head matmul -- captured as the head module's input via torch.nn.Module.register_forward_pre_hook; replay applies the head ONLY (no final norm at replay time: the capture already sits… See the full description on the dataset page: https://huggingface.co/datasets/malaiwah/qfs-smollm2-135m-wikitext2-gptq-g64-v1.meditsolutions__SmolLM2-MedIT-Upscale-2B-details
Dataset Card for Evaluation run of meditsolutions/SmolLM2-MedIT-Upscale-2B
Dataset automatically created during the evaluation run of model meditsolutions/SmolLM2-MedIT-Upscale-2B
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/meditsolutions__SmolLM2-MedIT-Upscale-2B-details.FlofloB__smollm2-135M_pretrained_1000k_fineweb-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_1000k_fineweb
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_1000k_fineweb
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_1000k_fineweb-details.FlofloB__smollm2-135M_pretrained_800k_fineweb_uncovai_selected-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_800k_fineweb_uncovai_selected
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_800k_fineweb_uncovai_selected
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_800k_fineweb_uncovai_selected-details.HuggingFaceTB__SmolLM2-1.7B-details
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM2-1.7B
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM2-1.7B
The dataset is composed of 38 configuration(s), each one corresponding 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/HuggingFaceTB__SmolLM2-1.7B-details.qfs-smollm2-135m-wikitext2-rtn-g64-v1
HF workflow ee13c03b2f256042a17c9817e17a2f20
A quant fidelity dataset in hidden form, produced by engines/tools/hf_capture.py from malaiwah/SmolLM2-135M-QFS-rtn-int4-g64.
The cut
the final hidden state handed to lm_head -- after the text model's final norm and immediately before the head matmul -- captured as the head module's input via torch.nn.Module.register_forward_pre_hook; replay applies the head ONLY (no final norm at replay time: the capture already sits… See the full description on the dataset page: https://huggingface.co/datasets/malaiwah/qfs-smollm2-135m-wikitext2-rtn-g64-v1.HuggingFaceTB__SmolLM2-135M-details
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM2-135M
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM2-135M
The dataset is composed of 38 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 results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/HuggingFaceTB__SmolLM2-135M-details.HuggingFaceTB__SmolLM2-360M-Instruct-details
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM2-360M-Instruct
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM2-360M-Instruct
The dataset is composed of 38 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/open-llm-leaderboard/HuggingFaceTB__SmolLM2-360M-Instruct-details.HuggingFaceTB__SmolLM2-1.7B-Instruct-details
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM2-1.7B-Instruct
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM2-1.7B-Instruct
The dataset is composed of 38 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/open-llm-leaderboard/HuggingFaceTB__SmolLM2-1.7B-Instruct-details.HuggingFaceTB__SmolLM2-135M-Instruct-details
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM2-135M-Instruct
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM2-135M-Instruct
The dataset is composed of 38 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/open-llm-leaderboard/HuggingFaceTB__SmolLM2-135M-Instruct-details.ewre324__Thinker-SmolLM2-135M-Instruct-Reasoning-details
Dataset Card for Evaluation run of ewre324/Thinker-SmolLM2-135M-Instruct-Reasoning
Dataset automatically created during the evaluation run of model ewre324/Thinker-SmolLM2-135M-Instruct-Reasoning
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/ewre324__Thinker-SmolLM2-135M-Instruct-Reasoning-details.FlofloB__smollm2-135M_pretrained_1400k_fineweb_uncovai_selected-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_1400k_fineweb_uncovai_selected
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_1400k_fineweb_uncovai_selected
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_1400k_fineweb_uncovai_selected-details.FlofloB__smollm2-135M_pretrained_600k_fineweb-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_600k_fineweb
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_600k_fineweb
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_600k_fineweb-details.FlofloB__smollm2-135M_pretrained_400k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_400k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_400k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_400k_fineweb_uncovai_human_removed-details.FlofloB__smollm2-135M_pretrained_1000k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_1000k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_1000k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_1000k_fineweb_uncovai_human_removed-details.bunnycore__SmolLM2-1.7-Persona-details
Dataset Card for Evaluation run of bunnycore/SmolLM2-1.7-Persona
Dataset automatically created during the evaluation run of model bunnycore/SmolLM2-1.7-Persona
The dataset is composed of 38 configuration(s), each one corresponding 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/bunnycore__SmolLM2-1.7-Persona-details.bunnycore__SmolLM2-1.7B-roleplay-lora-details
Dataset Card for Evaluation run of bunnycore/SmolLM2-1.7B-roleplay-lora
Dataset automatically created during the evaluation run of model bunnycore/SmolLM2-1.7B-roleplay-lora
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/bunnycore__SmolLM2-1.7B-roleplay-lora-details.prithivMLmods__SmolLM2-CoT-360M-details
Dataset Card for Evaluation run of prithivMLmods/SmolLM2-CoT-360M
Dataset automatically created during the evaluation run of model prithivMLmods/SmolLM2-CoT-360M
The dataset is composed of 38 configuration(s), each one corresponding 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/prithivMLmods__SmolLM2-CoT-360M-details.FlofloB__smollm2_pretrained_200k_fineweb-details
Dataset Card for Evaluation run of FlofloB/smollm2_pretrained_200k_fineweb
Dataset automatically created during the evaluation run of model FlofloB/smollm2_pretrained_200k_fineweb
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2_pretrained_200k_fineweb-details.FlofloB__smollm2-135M_pretrained_400k_fineweb-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_400k_fineweb
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_400k_fineweb
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_400k_fineweb-details.FlofloB__smollm2-135M_pretrained_1200k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_1200k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_1200k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_1200k_fineweb_uncovai_human_removed-details.FlofloB__smollm2-135M_pretrained_800k_fineweb-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_800k_fineweb
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_800k_fineweb
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_800k_fineweb-details.FlofloB__smollm2-135M_pretrained_200k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_200k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_200k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_200k_fineweb_uncovai_human_removed-details.FlofloB__smollm2-135M_pretrained_1400k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_1400k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_1400k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_1400k_fineweb_uncovai_human_removed-details.FlofloB__smollm2-135M_pretrained_200k_fineweb_uncovai_selected-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_200k_fineweb_uncovai_selected
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_200k_fineweb_uncovai_selected
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_200k_fineweb_uncovai_selected-details.FlofloB__smollm2-135M_pretrained_1200k_fineweb_uncovai_selected-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_1200k_fineweb_uncovai_selected
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_1200k_fineweb_uncovai_selected
The dataset is composed of 38 configuration(s), each one corresponding 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/FlofloB__smollm2-135M_pretrained_1200k_fineweb_uncovai_selected-details.FlofloB__smollm2-135M_pretrained_800k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_800k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_800k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_800k_fineweb_uncovai_human_removed-details.FlofloB__smollm2-135M_pretrained_600k_fineweb_uncovai_human_removed-details
Dataset Card for Evaluation run of FlofloB/smollm2-135M_pretrained_600k_fineweb_uncovai_human_removed
Dataset automatically created during the evaluation run of model FlofloB/smollm2-135M_pretrained_600k_fineweb_uncovai_human_removed
The dataset is composed of 38 configuration(s), each one corresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/FlofloB__smollm2-135M_pretrained_600k_fineweb_uncovai_human_removed-details.