Datasets used in "Understanding the Design Space and Cross-Modality Transfer for Vision-Language Models"
Rosie Zhao
rosieyzh
·
AI & ML interests
theory of machine learning, deep learning
Recent Activity
updated
a model 16 days ago
rosieyzh/rlvr_qwen15_gsm8k_rbz_642_epochs_ckpt_10_of_10 published
a model 16 days ago
rosieyzh/rlvr_qwen15_gsm8k_rbz_642_epochs_ckpt_10_of_10 updated
a model 16 days ago
rosieyzh/rlvr_qwen15_gsm8k_rbz_642_epochs_ckpt_9_of_10 Organizations
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_{32,64}_ckpt_{i}_of_10
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_{64,128}_ckpt_{i}_of_5
rosieyzh/rlvr_qwen15_gsm8k_rbz_{32, 64}_ckpt_{I}_of_10
rlvr_llama1_bleu_alma_rbz_{128,256}_ckpt_{i}_of_10
128: [7, 12, 21, 36, 62, 106, 182, 313, 535, 917]
256: [3, 6, 10, 18, 31, 53, 91, 156, 267, 458]
rosieyzh/rlvr_qwen15_warmstart_code200_rbz_{32, 64}_ckpt_{I}_of_10
rosieyzh/sft_qwen15_code200_lr_{1e-5, 5e-6}_{cosine, constant}_bsz_{64, 128}_ckpt_{i}_of_5
OLMo 1B model pretrained with Algebraic Stack, FineMath3, TinyGSM, OMI1, and OMI2. Includes checkpoints from doing PPO using GSM8K train.
-
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_ppo
Text Generation • 1B • Updated -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode1
Text Generation • 1B • Updated -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode2
Text Generation • 1B • Updated • 1 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode3
Text Generation • 1B • Updated • 3
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_{64,128}_ckpt_{i}_of_5
-
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
2B • Updated -
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_2_of_5
2B • Updated • 2 -
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
2B • Updated -
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
2B • Updated
rosieyzh/rlvr_llama1_rouge_xsum_rbz_{32,64}_ckpt_{i}_of_10
rosieyzh/rlvr_qwen15_warmstart_gsm8k_rbz_{32, 64}_ckpt_{I}_of_10
rlvr_llama1_warmstart_bleu_alma_rbz_{128, 256}_ckpt_{i}_of_10
rosieyzh/sft_llama1_alma_lr_1e-5_cosine_bsz_{64,128}_ckpt_{i}_of_5
rosieyzh/rlvr_qwen15_code200_rbz_{32, 64}_ckpt_{I}_of_10
Pretrained models from scratch used in "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining".
OLMo 1B model pretrained with Algebraic Stack, FineMath3, TinyGSM, and OpenMathInstruct2. Includes checkpoints from doing PPO using GSM8K train.
Datasets used in "Understanding the Design Space and Cross-Modality Transfer for Vision-Language Models"
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_{64,128}_ckpt_{i}_of_5
-
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
2B • Updated -
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_2_of_5
2B • Updated • 2 -
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
2B • Updated -
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
2B • Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_{32,64}_ckpt_{i}_of_10
rosieyzh/rlvr_llama1_rouge_xsum_rbz_{32,64}_ckpt_{i}_of_10
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_{64,128}_ckpt_{i}_of_5
rosieyzh/rlvr_qwen15_warmstart_gsm8k_rbz_{32, 64}_ckpt_{I}_of_10
rosieyzh/rlvr_qwen15_gsm8k_rbz_{32, 64}_ckpt_{I}_of_10
rlvr_llama1_warmstart_bleu_alma_rbz_{128, 256}_ckpt_{i}_of_10
rlvr_llama1_bleu_alma_rbz_{128,256}_ckpt_{i}_of_10
128: [7, 12, 21, 36, 62, 106, 182, 313, 535, 917]
256: [3, 6, 10, 18, 31, 53, 91, 156, 267, 458]
rosieyzh/sft_llama1_alma_lr_1e-5_cosine_bsz_{64,128}_ckpt_{i}_of_5
rosieyzh/rlvr_qwen15_warmstart_code200_rbz_{32, 64}_ckpt_{I}_of_10
rosieyzh/rlvr_qwen15_code200_rbz_{32, 64}_ckpt_{I}_of_10
rosieyzh/sft_qwen15_code200_lr_{1e-5, 5e-6}_{cosine, constant}_bsz_{64, 128}_ckpt_{i}_of_5
Pretrained models from scratch used in "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining".
OLMo 1B model pretrained with Algebraic Stack, FineMath3, TinyGSM, OMI1, and OMI2. Includes checkpoints from doing PPO using GSM8K train.
-
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_ppo
Text Generation • 1B • Updated -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode1
Text Generation • 1B • Updated -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode2
Text Generation • 1B • Updated • 1 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode3
Text Generation • 1B • Updated • 3
OLMo 1B model pretrained with Algebraic Stack, FineMath3, TinyGSM, and OpenMathInstruct2. Includes checkpoints from doing PPO using GSM8K train.