1 contributor

History: 4 commits

angelaupc

Meta-Llama-3-8B-Instruct-rm-Anthropic-hh-rlhf-concateye

08399bc verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

3.01 kB

Meta-Llama-3-8B-Instruct-rm-Anthropic-hh-rlhf-concateye 3 months ago
adapter_config.json

688 Bytes

meta-llama-Meta-Llama-3-8B-Instruct + argilla-dpo-mix-7k + True + True_batch_size_8_train_epochs_2_gradient_acum_steps_1_logging_steps_64_learning_rate_1e-05_lr_scheduler_type_cosine_with_min_lr_min_lr_ratio_0.6_weight_decay_0.1_seed_42 3 months ago
adapter_model.safetensors

2.12 GB
LFS

Meta-Llama-3-8B-Instruct-rm-Anthropic-hh-rlhf-concateye 3 months ago
special_tokens_map.json

761 Bytes

meta-llama-Meta-Llama-3-8B-Instruct + argilla-dpo-mix-7k + True + True_batch_size_4_train_epochs_2_gradient_acum_steps_1_logging_steps_64_learning_rate_5e-05_lr_scheduler_type_cosine_with_min_lr_min_lr_ratio_0.1_weight_decay_0.1_seed_42 3 months ago
tokenizer.json

9.09 MB

meta-llama-Meta-Llama-3-8B-Instruct + argilla-dpo-mix-7k + True + True_batch_size_4_train_epochs_2_gradient_acum_steps_1_logging_steps_64_learning_rate_5e-05_lr_scheduler_type_cosine_with_min_lr_min_lr_ratio_0.1_weight_decay_0.1_seed_42 3 months ago
tokenizer_config.json

52 kB

meta-llama-Meta-Llama-3-8B-Instruct + argilla-dpo-mix-7k + True + True_batch_size_4_train_epochs_2_gradient_acum_steps_1_logging_steps_64_learning_rate_5e-05_lr_scheduler_type_cosine_with_min_lr_min_lr_ratio_0.1_weight_decay_0.1_seed_42 3 months ago
training_args.bin
Detected Pickle imports (8)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "trl.trainer.reward_config.RewardConfig",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames"
How to fix it?
4.66 kB
LFS

Meta-Llama-3-8B-Instruct-rm-Anthropic-hh-rlhf-concateye 3 months ago

Detected Pickle imports (8)