radm
/

Qwen2.5-32B-simpo-LoRA

Generated from Trainer

Model card Files Files and versions Community

Qwen2.5-32B-simpo-LoRA

Ctrl+K

Ctrl+K

1 contributor

History: 9 commits

radm's picture

Update README.md

dface72 verified 4 days ago

.gitattributes

1.57 kB

first model version 6 months ago
README.md

1.58 kB

Update README.md 4 days ago
adapter_config.json

725 Bytes

first model version 6 months ago
adapter_model.safetensors

2.16 GB
LFS

first model version 6 months ago
added_tokens.json

605 Bytes

first model version 6 months ago
all_results.json

220 Bytes

first model version 6 months ago
merges.txt

1.67 MB

first model version 6 months ago
special_tokens_map.json

758 Bytes

first model version 6 months ago
tokenizer.json

7.03 MB
LFS

first model version 6 months ago
tokenizer_config.json

5.29 kB

first model version 6 months ago
train_results.json

220 Bytes

first model version 6 months ago
trainer_log.jsonl

90.9 kB

first model version 6 months ago
trainer_state.json

204 kB

first model version 6 months ago
training_args.bin
Detected Pickle imports (9)
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
5.37 kB
LFS

first model version 6 months ago
training_loss.png

45.6 kB

first model version 6 months ago
training_rewards_accuracies.png

64.4 kB

first model version 6 months ago
vocab.json

2.78 MB

first model version 6 months ago