Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
agurung
/
colar-qwen3-4b-ff-rl
like
0
Reinforcement Learning
Safetensors
qwen3
colar
latent-reasoning
flawed-fictions
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
colar-qwen3-4b-ff-rl
8.94 GB
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
agurung
Archive exact-epoch16-step9856-val_reward=0.6875 from local CoLAR export
31f153c
verified
9 days ago
.gitattributes
Safe
1.57 kB
Upload checkpoint: best-epoch24-val_reward=0.6719
about 1 month ago
README.md
Safe
1.83 kB
Archive exact-epoch16-step9856-val_reward=0.6875 from local CoLAR export
9 days ago
chat_template.jinja
Safe
2.63 kB
Upload checkpoint: best-epoch24-val_reward=0.6719
about 1 month ago
config.json
Safe
1.59 kB
Upload checkpoint: best-epoch24-val_reward=0.6719
about 1 month ago
export_meta.json
Safe
172 Bytes
Archive exact-epoch16-step9856-val_reward=0.6875 from local CoLAR export
9 days ago
extra_state.pt
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch.BFloat16Storage"
What is a pickle import?
881 MB
xet
Archive exact-epoch16-step9856-val_reward=0.6875 from local CoLAR export
9 days ago
generation_config.json
Safe
190 Bytes
Upload checkpoint: best-epoch24-val_reward=0.6719
about 1 month ago
latent_metadata.json
Safe
1.39 kB
Archive exact-epoch16-step9856-val_reward=0.6875 from local CoLAR export
9 days ago
model.safetensors
Safe
8.04 GB
xet
Archive exact-epoch16-step9856-val_reward=0.6875 from local CoLAR export
9 days ago
tokenizer.json
11.4 MB
xet
Upload checkpoint: best-epoch24-val_reward=0.6719
about 1 month ago
tokenizer_config.json
Safe
658 Bytes
Upload checkpoint: best-epoch24-val_reward=0.6719
about 1 month ago