TienAnh
/

stage3-moe-ft-llavaqwen1.5-0.5b-vista-4ep_moe

moe_llava_qwen1_5

Generated from Trainer

Model card Files Files and versions Community

stage3-moe-ft-llavaqwen1.5-0.5b-vista-4ep_moe

1 contributor

History: 3 commits

TienAnh's picture

edit pad_token_id, fix Padding_idx must be within num_embeddings

dd1ea19 verified 4 months ago

.gitattributes

1.52 kB

initial commit 4 months ago
README.md

1.38 kB

Model save 4 months ago
added_tokens.json

105 Bytes

Model save 4 months ago
config.json

2.04 kB

edit pad_token_id, fix Padding_idx must be within num_embeddings 4 months ago
generation_config.json

117 Bytes

Model save 4 months ago
merges.txt

1.67 MB

Model save 4 months ago
model.safetensors

4.1 GB
LFS

Model save 4 months ago
pytorch_model.bin

1.74 GB
LFS

Model save 4 months ago
special_tokens_map.json

398 Bytes

Model save 4 months ago
tokenizer_config.json

1.51 kB

Model save 4 months ago
trainer_state.json

223 kB

Model save 4 months ago
training_args.bin
Detected Pickle imports (11)
- "moellava.train.train.TrainingArguments",
- "accelerate.utils.dataclasses.DistributedType",
- "torch.float16",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "torch.device",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DeepSpeedPlugin"
How to fix it?
5.95 kB
LFS

Model save 4 months ago
vocab.json

3.38 MB

Model save 4 months ago