Evangeline Shen's picture

2 2

Evangeline Shen

Evangelinejy

·

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

chess-pre-to-post/pretraining_dataset_v1_tokenized

published a model 1 day ago

chess-pre-to-post/pretraining_dataset_v1_tokenized

updated a model 7 days ago

Evangelinejy/llama_8b_math_2048

View all activity

Organizations

Evangelinejy 's models 61

Evangelinejy/llama-32-3b-midtrain-openthoughts-think-8192-epoch1.0-bs4

175k • Updated Feb 7 • 10

Evangelinejy/llama-32-3b-instruct-openthoughts-think-8192-epoch1.0-bs4

175k • Updated Feb 7 • 7

Evangelinejy/llama-32-3b-instruct-openthoughts-nothink-bs4-epoch2.0-ctx8192-ga2-lr1e-05-wr0.1-n4

175k • Updated Jan 26

Evangelinejy/llama-32-3b-instruct-openthoughts-nothink-bs4-epoch1.0-ctx8192-ga2-lr1e-05-wr0.1-n4

175k • Updated Jan 26

Evangelinejy/llama3b_base_openthoughts_solution_only-bs4-epoch1.0-ctx8192-ga1-lr5e-05-wr0.1-n4

Text Generation • 175k • Updated Jan 22 • 1

Evangelinejy/llama3b_midtrain_openthoughts_solution_only-bs4-epoch1.0-ctx8192-ga1-lr5e-05-wr0.1-n4

Text Generation • 175k • Updated Jan 22 • 9

Evangelinejy/Qwen3_0.6B_LanTokenizer_ctx2048

0.4B • Updated Jan 5 • 1

Evangelinejy/qwen25-7b-prm_demo-bs2-epoch3.0-ctx4096-ga2-lr1e-05-wr0.1-n4

Text Generation • 333k • Updated Dec 20, 2025 • 1

Evangelinejy/llama-32-3b-instruct-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga2-lr1e-05-wr0.1-n4

175k • Updated Nov 22, 2025 • 3

Evangelinejy/llama3b-instruct-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga2-lr1e-05-wr0.1-n4

175k • Updated Nov 22, 2025

Evangelinejy/llama3b-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 15, 2025 • 6

Evangelinejy/llama3b-midtrain-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 15, 2025 • 1

Evangelinejy/octothinker-3b-short-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 15, 2025

Evangelinejy/octothinker-3b-hybrid-base-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 15, 2025 • 1

Evangelinejy/llama3b-midtrain-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga1-lr5e-06-wr0.1-n4

175k • Updated Nov 12, 2025 • 9

Evangelinejy/octothinker-short-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga1-lr5e-06-wr0.1-n4

175k • Updated Nov 12, 2025

Evangelinejy/octothinker-3b-short-base-data_sft_50k_leon_nemotron-bs4-epoch1.0-ctx4096-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 12, 2025 • 1

Evangelinejy/octothinker-3b-hybrid-base-data_sft_50k_leon_nemotron-bs4-epoch1.0-ctx4096-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 12, 2025

Evangelinejy/llama3b-midtrain-data_sft_50k_leon_nemotron-bs4-epoch1.0-ctx4096-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 10, 2025

Evangelinejy/qwen15b-midtrain-data_sft_50k_leon_nemotron-bs4-epoch1.0-ctx4096-ga1-lr1e-06-wr0.1-n4

2B • Updated Nov 10, 2025 • 3

Evangelinejy/qwen25-15b-data_sft_50k_leon_nemotron-bs4-epoch1.0-ctx4096-ga1-lr1e-05-wr0.1-n4

2B • Updated Nov 9, 2025

Evangelinejy/llama-32-3b-data_sft_50k_leon_nemotron-bs4-epoch1.0-ctx4096-ga1-lr1e-05-wr0.1-n4

175k • Updated Nov 9, 2025

Evangelinejy/reasoning-gym-graph-datasets-easy

Updated Oct 15, 2025

Evangelinejy/reasoning-gym-logic-puzzle-datasets

Updated Oct 13, 2025

Evangelinejy/reasoning-gym-graph-datasets

Updated Oct 5, 2025

Evangelinejy/Qwen2.5-1.5B-Instruct_MATH-lighteval_epoch_1_bs_4_lr_2e-05_length_4096_G_7

Text Generation • 2B • Updated Mar 1, 2025 • 3

Evangelinejy/Qwen2.5-1.5B-Instruct_MATH-lighteval_epoch_1_bs_4_lr_2e-05_length_4096_G_8

Updated Mar 1, 2025

Evangelinejy/Qwen2.5-1.5B-Instruct_MATH-lighteval_epoch_1_bs_8_lr_2e-05_length_2048_G_16

Text Generation • 2B • Updated Feb 28, 2025 • 5

Evangelinejy/Qwen2.5-1.5B-Open-R1-GRPO

Text Generation • 2B • Updated Feb 28, 2025 • 1

Evangelinejy/contamination-models-truthfulQA-EleutherAI-pythia-6.9b-default

Text Generation • 7B • Updated Dec 21, 2024 • 1