zsqzz/Qwen3-1.7B_openthoughts_sft_step198
Text Generation • 2B • Updated • 6
siqi zhu
zsqzz
AI & ML interests
None yet
Recent Activity
upvoted an article 5 days ago
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL upvoted a paper 16 days ago
Interactive Evaluation Requires a Design Science upvoted a paper 17 days ago
Code as Agent HarnessOrganizations
zsqzz/Qwen3-1.7B_opsd_masked_grpo_dapo_hf
Text Generation • 2B • Updated • 5
zsqzz/anlp-hw2-outputs
Updated
zsqzz/cs546_hw1
Text Classification • 67M • Updated
zsqzz/game_0709
3B • Updated • 3
zsqzz/game_step50_jul03
3B • Updated
zsqzz/opt-125m
Updated
zsqzz/0520-distillbert-llama3-70b-class-trainbucketsize820-sharegpt
Updated
zsqzz/0520-distillbert-llama3-70b-class-trainbucketsize820-lmsys
Updated
zsqzz/0520-distillbert-llama3-70b-score-trainbucketsize10-lmsys
Updated
zsqzz/0520-distillbert-llama3-70b-score-trainbucketsize10-sharegpt
Updated
zsqzz/0520-opt-125m-llama3-70b-score-trainbucketsize10-lmsys
Updated
zsqzz/0520-opt-125m-llama3-70b-class-trainbucketsize820-sharegpt
Updated
zsqzz/0520-opt-125m-llama3-70b-class-trainbucketsize820-lmsys
Updated
zsqzz/0520-opt-125m-llama3-70b-score-trainbucketsize10-sharegpt
Updated
zsqzz/0520-opt-350m-llama3-70b-score-trainbucketsize10-sharegpt
Updated
zsqzz/0520-opt-350m-llama3-70b-score-trainbucketsize10-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize50-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize820-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize100-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize10-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize1-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize50-sharegpt
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize100-sharegpt
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize10-sharegpt
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize1-sharegpt
Updated
zsqzz/0520-opt-350m-llama3-70b-class-trainbucketsize820-sharegpt
Updated
zsqzz/repo_id
Updated
zsqzz/0520-opt-350m-llama3-70b-rank-trainbucketsize10-lmsys
Updated
zsqzz/0520-opt-350m-llama3-70b-rank-trainbucketsize10-sharegpt
Updated