1 contributor

History: 7 commits

liswei

Update model with 2x training data and more efficient vocabulary

ee1b4c2 verified about 2 months ago

runs
Update model with 2x training data and more efficient vocabulary about 2 months ago
.gitattributes

1.52 kB

initial commit 2 months ago
README.md

1.07 kB

Update model with 2x training data and more efficient vocabulary about 2 months ago
all_results.json

223 Bytes

Update model with 2x training data and more efficient vocabulary about 2 months ago
config.json

1.43 kB

Update model with 2x training data and more efficient vocabulary about 2 months ago
configuration_openelm.py

14.3 kB

Upload OpenELMForCausalLM 2 months ago
generation_config.json

111 Bytes

Upload OpenELMForCausalLM 2 months ago
model.safetensors

1.24 GB
LFS

Update model with 2x training data and more efficient vocabulary about 2 months ago
modeling_openelm.py

39.3 kB

Upload OpenELMForCausalLM 2 months ago
special_tokens_map.json

437 Bytes

Update model with 2x training data and more efficient vocabulary about 2 months ago
tokenizer.json

3.07 MB

Update model with 2x training data and more efficient vocabulary about 2 months ago
tokenizer.model

967 kB
LFS

Update model with 2x training data and more efficient vocabulary about 2 months ago
tokenizer_config.json

1.4 kB

Update model with 2x training data and more efficient vocabulary about 2 months ago
train_results.json

223 Bytes

Update model with 2x training data and more efficient vocabulary about 2 months ago
trainer_log.jsonl

912 kB

Update model with 2x training data and more efficient vocabulary about 2 months ago
trainer_state.json

713 kB

Update model with 2x training data and more efficient vocabulary about 2 months ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.18 kB
LFS

Update model with 2x training data and more efficient vocabulary about 2 months ago
training_loss.png

30.3 kB

Update model with 2x training data and more efficient vocabulary about 2 months ago

Detected Pickle imports (9)