Models

qwen3_4b_easy_rl_new

Qwen2.5-7B-TTT

Mira-v1.20-27B-dpo

qwen3-warmup-sft

swesmith-nl2bash-stack-bugsseq

qwen3_4b_base_easy_rl_final

DUSK-target-woD1-llama3.1-8b-instruct

open-thoughts-4-code-qwen3-32b-annotated-gbs256-4node

Affine-5Ec26gNVCcavNTHrpsrKsdzBTM5QE1cvYhcWtaLriepqAeoJ

Qwen3-4B-TIR

Affine-CR7

Affine-20251223-3325-765

binary_accfmt_MRL4096_ROLLOUT4_LR2e-6_step30

bioinstruct-llama3.2-1b-merged

affine-forward00

7b_perprompt_step_332_final

qwen3_1.7b_easy_rl_fixed_gamma_1

Affine-ana8-3

ShweYon-Qwen2.5-Burmese-1.5B-v1.2

affine-001

llama3-8b-full-sft-v3

Qwen3-4B-Thinking-2507-exp02

qwen3_1.7b_sft_final_easy_reinforce_ours_adv_fixed_gamma_0.9

qwen-recipe-merged

InjecAgent-Llama-3.1-8B-Instruct-optim-fix-10

InjecAgent-Llama-3.1-8B-Instruct-optim-fix-15

random-v3

affine-001

Llama-3.1-8B-Instruct_SFT_Math-220kv00.19

sft_qwen32b

Qwen2.5-7B-Instruct-SFT-Pubmed-16bit-DFT

sleeper-proxy-tinyllama-1.1b

parti_30_full

gemma3-1b-Indian-history

affine-v124

appworld_distillation_sft_v2-SFT-Qwen3-4B-Instruct-2507

qwen3-dpo-tulu

SmolLM3-Mid-Second-Round

full_sft_5

SmolLM3-SFT-Second-Round

qwen_omi2_step100

octothinker-hybrid-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga1-lr5e-06-wr0.1-n4