cs-552-2026-busybees
/

group_model

Model card Files Files and versions

3.46 GB

Ctrl+K

Ctrl+K

3 contributors

History: 20 commits

sophieur444's picture

Restore generation_config.json from commit d6c27be (working sampling config)

080fbf7 verified about 2 months ago

.gitattributes

1.57 kB
Upload initial group model checkpoint 2 months ago
EVAL_REPORT.md

6.58 kB
Automated MNLP evaluation report (2026-05-21) (#1) 2 months ago
added_tokens.json

707 Bytes
v3 update 2 months ago
chat_template.jinja

4.2 kB
restore thinking mode 2 months ago
config.json

1.36 kB
v3 update 2 months ago
generation_config.json

214 Bytes
Restore generation_config.json from commit d6c27be (working sampling config) about 2 months ago
group_eval.py

5.36 kB
transport: group_eval.py with env MAX_TOKENS (script only, no weights) about 2 months ago
merges.txt

1.67 MB
v3 update 2 months ago
model.safetensors

3.44 GB
xet

Set group_model to fb56cd1e weights (per team decision) about 2 months ago
special_tokens_map.json

499 Bytes
group_model: proposal recipe (OpenThoughts/LIMO/OpenMathReasoning + distilled safety + MGSM) 2 months ago
tokenizer.json

11.4 MB
xet

v3 update 2 months ago
tokenizer_config.json

5.4 kB
group_model: proposal recipe (OpenThoughts/LIMO/OpenMathReasoning + distilled safety + MGSM) 2 months ago
train_group_v2.py

15.6 kB
group v2 script (transport) about 2 months ago
train_group_v3.py

15.6 kB
add v3 training script about 2 months ago
train_group_v4_boxfix.py

12.1 kB
transport: train_group_v4_boxfix.py (script only, no weights) about 2 months ago
train_group_v5_frombase.py

12.4 kB
Upload train_group_v5_frombase.py with huggingface_hub about 2 months ago
vocab.json

2.78 MB
v3 update 2 months ago