Mantis-VL
/

llava_siglip_llama3_8b_finetune_obelics_min_8192_lora

4-bit precision

Model card Files Files and versions Community

llava_siglip_llama3_8b_finetune_obelics_min_8192_lora

1 contributor

History: 13 commits

DongfuJiang's picture

Upload tokenizer.json with huggingface_hub

18d17ec verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

5.13 kB

Upload README.md with huggingface_hub 3 months ago
adapter_config.json

762 Bytes

Training in progress, step 1000 3 months ago
adapter_model.safetensors

722 MB
LFS

Upload adapter_model.safetensors with huggingface_hub 3 months ago
config.json

1.69 kB

Upload config.json with huggingface_hub 3 months ago
non_lora_trainables.bin

912 Bytes
LFS

Upload non_lora_trainables.bin with huggingface_hub 3 months ago
preprocessor_config.json

669 Bytes

Training in progress, step 500 3 months ago
special_tokens_map.json

387 Bytes

Training in progress, step 500 3 months ago
tokenizer.json

9.09 MB

Training in progress, step 500 3 months ago
tokenizer_config.json

51.7 kB

Training in progress, step 500 3 months ago
training_args.bin
Detected Pickle imports (12)
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.SchedulerType",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames"
How to fix it?
6.52 kB
LFS

Training in progress, step 1000 3 months ago