Ctrl+K

1 contributor

History: 23 commits

Naataan

Adds GGML model file (16-bit)

0c03977 verified about 2 months ago

.gitattributes

1.52 kB

initial commit 10 months ago
README.md

16 kB

Update README.md 6 months ago
added_tokens.json

34.6 kB

Initial commit 10 months ago
all_results.json

200 Bytes

Initial commit 10 months ago
config.json

1.3 kB

Update config.json 9 months ago
generation_config.json

76.1 kB

add timestamp tokens to suppress tokens 8 months ago
ggml-model.bin

3.09 GB
LFS

Adds GGML model file (16-bit) about 2 months ago
merges.txt

366 kB

update tokenizer with softprompts for next version 8 months ago
model.safetensors

3.22 GB
LFS

Initial commit 10 months ago
normalizer.json

52.7 kB

Initial commit 10 months ago
preprocessor_config.json

340 Bytes

Initial commit 10 months ago
special_tokens_map.json

2.19 kB

Initial commit 10 months ago
tokenizer_config.json

284 kB

update tokenizer with softprompts for next version 8 months ago
train_results.json

200 Bytes

Initial commit 10 months ago
trainer_state.json

16.1 kB

Initial commit 10 months ago
training_args.bin
Detected Pickle imports (12)
- "transformers.generation.configuration_utils.GenerationConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "torch.float16",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "torch.device",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
How to fix it?
26.6 kB
LFS

Initial commit 10 months ago
vocab.json

878 kB

Initial commit 10 months ago

Detected Pickle imports (12)