dfrees
/

llama-1b-instruct-dpo

4-bit precision

Model card Files Files and versions Community

llama-1b-instruct-dpo

1 contributor

History: 6 commits

dfrees's picture

Uploading merged DPO-trained model

11e04b0 verified 4 months ago

.gitattributes

1.57 kB

Uploading DPO-trained model 4 months ago
README.md

5.11 kB

Uploading merged DPO-trained model 4 months ago
adapter_config.json

656 Bytes

Uploading merged DPO-trained model 4 months ago
adapter_model.safetensors

3.42 MB
LFS

Uploading merged DPO-trained model 4 months ago
config.json

1.41 kB

Uploading merged DPO-trained model 4 months ago
generation_config.json

184 Bytes

Uploading merged DPO-trained model 4 months ago
model.safetensors

1.56 GB
LFS

Uploading merged DPO-trained model 4 months ago
special_tokens_map.json

325 Bytes

Uploading merged DPO-trained model 4 months ago
tokenizer.json

9.09 MB
LFS

Uploading merged DPO-trained model 4 months ago
tokenizer_config.json

54.6 kB

Uploading merged DPO-trained model 4 months 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
LFS

Uploading merged DPO-trained model 4 months ago