dfrees
/

llama-1b-instruct-dpo

4-bit precision

Model card Files Files and versions

llama-1b-instruct-dpo

1.57 GB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

dfrees's picture

Uploading merged DPO-trained model

11e04b0 verified almost 2 years ago

.gitattributes

1.57 kB
Uploading DPO-trained model almost 2 years ago
README.md

5.11 kB
Uploading merged DPO-trained model almost 2 years ago
adapter_config.json

656 Bytes
Uploading merged DPO-trained model almost 2 years ago
adapter_model.safetensors

3.42 MB
xet

Uploading merged DPO-trained model almost 2 years ago
config.json

1.41 kB
Uploading merged DPO-trained model almost 2 years ago
generation_config.json

184 Bytes
Uploading merged DPO-trained model almost 2 years ago
model.safetensors

1.56 GB
xet

Uploading merged DPO-trained model almost 2 years ago
special_tokens_map.json

325 Bytes
Uploading merged DPO-trained model almost 2 years ago
tokenizer.json

9.09 MB
xet

Uploading merged DPO-trained model almost 2 years ago
tokenizer_config.json

54.6 kB
Uploading merged DPO-trained model almost 2 years ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.11 kB
xet

Uploading merged DPO-trained model almost 2 years ago