DatPySci
/

RLVR-SGDM-Gap

Model card Files Files and versions

1.59 TB

Ctrl+K

Ctrl+K

1 contributor

History: 47 commits

DatPySci's picture

Upload folder using huggingface_hub

7e112f2 verified about 2 months ago

Llama-3.2-3B-Instruct-polaris-GRPO--bsz128
Add files using upload-large-folder tool about 2 months ago
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16
Add files using upload-large-folder tool about 2 months ago
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256
Add files using upload-large-folder tool about 2 months ago
Llama-3.2-3B-Instruct-polaris-GRPO--bsz32
Add files using upload-large-folder tool about 2 months ago
Llama-3.2-3B-Instruct-polaris-GRPO--bsz512
Add files using upload-large-folder tool about 2 months ago
Llama-3.2-3B-Instruct-polaris-GRPO--bsz64
Add files using upload-large-folder tool about 2 months ago
Qwen2.5-3B-Instruct-polaris-AdamW-GRPO
Upload folder using huggingface_hub about 2 months ago
kfac_out
Upload folder using huggingface_hub about 2 months ago
synthetic
Delete synthetic/Qwen2.5-0.5B-GSM8k-synthetic.jsonl about 2 months ago
.gitattributes

11.2 kB
Upload synthetic/Qwen2.5-3B-Instruct-Polaris/polaris_t0.7_p1.0_n32-MNT3072.jsonl with huggingface_hub about 2 months ago