2 contributors

History: 6 commits

teknium

Enable 8/4bit quantization

3bbb04a over 1 year ago

.gitattributes

1.48 kB

initial commit over 1 year ago
README.md

2.8 kB

Update README.md over 1 year ago
adapt_tokenizer.py

1.75 kB

Upload 19 files over 1 year ago
added_tokens.json

19 Bytes

Upload 19 files over 1 year ago
attention.py

16.2 kB

Upload 19 files over 1 year ago
blocks.py

2.53 kB

Upload 19 files over 1 year ago
config.json

1.23 kB

Fixing path issues to fix loading of models with Auto* classes. (#1) over 1 year ago
configuration_mpt.py

9.2 kB

Upload 19 files over 1 year ago
generation_config.json

91 Bytes

Upload 19 files over 1 year ago
hf_prefixlm_converter.py

27.2 kB

Upload 19 files over 1 year ago
meta_init_context.py

3.64 kB

Upload 19 files over 1 year ago
modeling_mpt.py

17.6 kB

Enable 8/4bit quantization over 1 year ago
norm.py

2.56 kB

Upload 19 files over 1 year ago
param_init_fns.py

12.6 kB

Upload 19 files over 1 year ago
pytorch_model.bin

5.2 GB
LFS

Upload 19 files over 1 year ago
replit_lm_tokenizer.py

6.26 kB

Upload 19 files over 1 year ago
special_tokens_map.json

109 Bytes

Upload 19 files over 1 year ago
spiece.model

708 kB
LFS

Upload 19 files over 1 year ago
tokenizer_config.json

425 Bytes

Upload 19 files over 1 year ago
trainer_state.json

855 Bytes

Upload 19 files over 1 year ago
training_args.bin
Detected Pickle imports (8)
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.IntervalStrategy",
- "__main__.TrainingArguments",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
3.96 kB
LFS

Upload 19 files over 1 year ago

Detected Pickle imports (8)