Update README.md
1d209a4 verified - benchmarks Delete benchmarks/bench_20260201_060606.json
- checkpoint-5000 Upload folder using huggingface_hub
- evals Upload evals/eval_20260131_110401.csv with huggingface_hub
- 1.65 kB Upload Shaista-pro config and adapter weights
- 1.51 kB Update README.md
- 972 Bytes Upload Shaista-pro config and adapter weights
- 54.5 MB Upload Shaista-pro config and adapter weights
- 922 Bytes Upload LlamaForCausalLM
- 229 Bytes Upload LlamaForCausalLM
- 16.1 GB Upload LlamaForCausalLM
- 109 MB Upload Shaista-pro config and adapter weights
rng_state.pth Detected Pickle imports (7)
- "_codecs.encode",
- "torch._utils._rebuild_tensor_v2",
- "numpy.dtype",
- "numpy._core.multiarray._reconstruct",
- "torch.ByteStorage",
- "collections.OrderedDict",
- "numpy.ndarray"
How to fix it?
14.6 kB Upload Shaista-pro config and adapter weights - 1.47 kB Upload Shaista-pro config and adapter weights
- 459 Bytes Upload Shaista-pro config and adapter weights
- 17.2 MB Upload tokenizer
- 519 Bytes Upload tokenizer
- 294 kB Upload Shaista-pro config and adapter weights
training_args.bin Detected Pickle imports (10)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device",
- "trl.trainer.sft_config.SFTConfig",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
6.35 kB Upload Shaista-pro config and adapter weights