pszemraj
/

opt-peter-1.3B

Text Generation Transformers PyTorch TensorBoard opt generated_from_trainer non-commercial dialogue chatbot Inference Endpoints text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

3 contributors

History: 13 commits

pszemraj's picture

ArthurZ's picture

ArthurZ HF staff

Update config.json (#3)

bff665b almost 2 years ago

logs
add model files straight-outta-trainer almost 2 years ago
.gitattributes

1.17 kB

initial commit almost 2 years ago
.gitignore

13 Bytes

add model files straight-outta-trainer almost 2 years ago
README.md

2.48 kB

Update README.md almost 2 years ago
config.json

690 Bytes

Update config.json (#3) almost 2 years ago
latest

14 Bytes

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
merges.txt

456 kB

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "collections.OrderedDict"
What is a pickle import?
5.26 GB
LFS

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
special_tokens_map.json

351 Bytes

add tokenizer almost 2 years ago
tokenizer.json

2.11 MB

add tokenizer almost 2 years ago
tokenizer_config.json

745 Bytes

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
trainer_state.json

3.32 kB

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
training_args.bin
Detected Pickle imports (8)
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.training_args.TrainingArguments",
- "transformers.training_args.OptimizerNames",
- "transformers.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.SchedulerType",
- "torch.float16"
How to fix it?
4.34 kB
LFS

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
vocab.json

798 kB

add new checkpoint trained for a hundred steps with smaller max grad norm and weight decay almost 2 years ago
zero_to_fp32.py

18.9 kB

update model with approx 1.6 epochs training almost 2 years ago