billyenrizky
/

FS-DFM-1.3B-FlowGRPO

Reinforcement Learning

discrete-flow-matching

web-action-planning

Model card Files Files and versions

FS-DFM-1.3B-FlowGRPO / final

14.6 MB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

billyenrizky's picture

Upload FS-DFM-1.3B-FlowGRPO checkpoint

4f74292 verified about 2 months ago

lora_weights.pt
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
11.1 MB
xet

Upload FS-DFM-1.3B-FlowGRPO checkpoint about 2 months ago
tokenizer.json

3.56 MB
Upload FS-DFM-1.3B-FlowGRPO checkpoint about 2 months ago
tokenizer_config.json

297 Bytes
Upload FS-DFM-1.3B-FlowGRPO checkpoint about 2 months ago