7 days ago
-
docs: add Apache-2.0 license, NOTICE and dataset attributions
-
Upload checkpoints/pretrain_p2/epoch=1-step=8000.ckpt (7.9GB)
-
Upload checkpoints/pretrain_p2/last.ckpt (7.9GB)
-
Upload checkpoints/finetune_distill/epoch=2-step=6016.ckpt (7.9GB)
-
Upload checkpoints/finetune_distill/last.ckpt (7.9GB)
-
Upload checkpoints/finetune/last.ckpt (7.9GB)
-
Upload checkpoints/pretrain/last_12500.ckpt (7.9GB)
-
Upload checkpoints/pretrain_p2/model.pt (2.6GB)
-
Upload checkpoints/finetune_distill/model.pt (2.6GB)
-
Upload checkpoints/finetune/model.pt (2.6GB)
-
Upload checkpoints/pretrain/model.pt (2.6GB)
-
Upload tokenizer/boccaccio-32k.json
-
Upload tokenizer/boccaccio-32k.json
-
Upload checkpoints/pretrain_p2/model.pt
-
Upload checkpoints/pretrain_p2/last.ckpt
-
Upload checkpoints/pretrain_p2/epoch=1-step=8000.ckpt
-
Upload checkpoints/pretrain/model.pt
-
Upload checkpoints/pretrain/last_12500.ckpt
-
Upload checkpoints/finetune_distill/model.pt
-
Upload checkpoints/finetune_distill/last.ckpt
-
Upload checkpoints/finetune_distill/epoch=2-step=6016.ckpt
-
Upload checkpoints/finetune/model.pt
-
Upload checkpoints/finetune/last.ckpt
-
Upload checkpoints/pretrain/model.pt with huggingface_hub
-
Upload tokenizer/boccaccio-32k.json with huggingface_hub
-
Upload checkpoints/pretrain_p2/model.pt with huggingface_hub
-
Upload checkpoints/pretrain_p2/last.ckpt with huggingface_hub
-
Upload checkpoints/pretrain_p2/epoch=1-step=8000.ckpt with huggingface_hub
-
Upload checkpoints/pretrain/model.pt with huggingface_hub
-
Upload checkpoints/pretrain/last_12500.ckpt with huggingface_hub
-
Upload checkpoints/finetune_distill/model.pt with huggingface_hub
-
Upload checkpoints/finetune_distill/last.ckpt with huggingface_hub
-
Upload checkpoints/finetune_distill/epoch=2-step=6016.ckpt with huggingface_hub
-
Upload checkpoints/finetune/model.pt with huggingface_hub
-
Upload checkpoints/finetune/last.ckpt with huggingface_hub
-
Upload folder using huggingface_hub
-
initial commit