5456es
/

implicit_reward_Qwen2.5-0.5B-Instruct_prune_0.3-sigmoid

preference-learning

Model card Files Files and versions

implicit_reward_Qwen2.5-0.5B-Instruct_prune_0.3-sigmoid

989 MB

1 contributor

History: 5 commits

5456es's picture

Upload rng_state_1.pth with huggingface_hub

429f3de verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
config.json

683 Bytes

Upload config.json with huggingface_hub 3 months ago
model.safetensors

988 MB
xet

Upload model.safetensors with huggingface_hub 3 months ago
rng_state_1.pth
Detected Pickle imports (7)
- "collections.OrderedDict",
- "numpy._core.multiarray._reconstruct",
- "torch._utils._rebuild_tensor_v2",
- "torch.ByteStorage",
- "numpy.ndarray",
- "_codecs.encode",
- "numpy.dtype"
How to fix it?
16.4 kB
xet

Upload rng_state_1.pth with huggingface_hub 3 months ago
trainer_state.json

548 kB

Upload trainer_state.json with huggingface_hub 3 months ago