chitanda
/

deepseek-math.7b.ins.meta_math_cot.math55k.n5.critic_correct.dpo.H100.w4.v2.0.s42

Model card Files Files and versions Community

deepseek-math.7b.ins.meta_math_cot.math55k.n5.critic_correct.dpo.H100.w4.v2.0.s42 / checkpoint-400

13.8 GB

1 contributor

History: 1 commit

chitanda's picture

Upload folder using huggingface_hub

9582185 verified 7 months ago

config.json

770 Bytes

Upload folder using huggingface_hub 7 months ago
generation_config.json

147 Bytes

Upload folder using huggingface_hub 7 months ago
math500.test.wrong_correct.v1.0.0shot.n5.tem1.0.json

2.77 MB

Upload folder using huggingface_hub 7 months ago
math500.test.wrong_correct.v1.0.0shot.n5.tem1.0.jsonl

2.7 MB

Upload folder using huggingface_hub 7 months ago
math500.test.wrong_correct.v1.0.0shot.n5.tem1.0.metrics.json

97 Bytes

Upload folder using huggingface_hub 7 months ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
13.8 GB
LFS

Upload folder using huggingface_hub 7 months ago
special_tokens_map.json

620 Bytes

Upload folder using huggingface_hub 7 months ago
tokenizer.json

4.61 MB

Upload folder using huggingface_hub 7 months ago
tokenizer_config.json

1.51 kB

Upload folder using huggingface_hub 7 months ago
training_config.yaml

3.92 kB

Upload folder using huggingface_hub 7 months ago