Update README.md
45dead3
verified
-
onnx
Upload improved fp16 ONNX weights (#6)
-
runs
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
1.52 kB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
5.67 kB
Update README.md
-
783 Bytes
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
861 Bytes
Update config.json
-
586 Bytes
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
132 Bytes
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
466 kB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
269 MB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
655 Bytes
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
2.1 MB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
3.76 kB
chat template
-
232 Bytes
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
57.2 kB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
training_args.bin
Detected Pickle imports (13)
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "alignment.configs.DPOConfig",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
How to fix it?
6.52 kB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2
-
801 kB
Duplicate from HuggingFaceTB/smollm2-135M-8k-lc100k-dpo-ultaf-ep2