A2H0H0R1
/

Qwen-7B-Chat-Int4-Qlora-rice-new-long

Model card Files Files and versions Community

Qwen-7B-Chat-Int4-Qlora-rice-new-long

1 contributor

History: 3 commits

A2H0H0R1's picture

Upload generation_config.json

064ddea verified 12 months ago

.gitattributes

1.52 kB

initial commit 12 months ago
README.md

5.1 kB

Upload folder using huggingface_hub 12 months ago
adapter_config.json

618 Bytes

Upload folder using huggingface_hub 12 months ago
adapter_model.safetensors

286 MB
LFS

Upload folder using huggingface_hub 12 months ago
generation_config.json

273 Bytes

Upload generation_config.json 12 months ago
qwen.tiktoken

2.56 MB

Upload folder using huggingface_hub 12 months ago
special_tokens_map.json

35 Bytes

Upload folder using huggingface_hub 12 months ago
tokenizer_config.json

324 Bytes

Upload folder using huggingface_hub 12 months ago
trainer_state.json

6.94 kB

Upload folder using huggingface_hub 12 months ago
training_args.bin
Detected Pickle imports (11)
- "__main__.TrainingArguments",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "torch.float16"
How to fix it?
6.26 kB
LFS

Upload folder using huggingface_hub 12 months ago