Models

qwen3-8B-ZH-SynthDolly-1A

qwen3-8B-PT-SynthDolly-1A

Qwen3-1.7B-Base_dsum_3_6_rel_1e-1_alt_oracle1_noisy9_1p0_0p0_1p0_grpo_42_rule

qwen3_8b_vdrop75_propqgen_annealed_solver_v3

Meet7.1_0.6b_Exp

a1-codeactinstruct

gemma-3-4b-it-vietnamese-r16

Qwen3-1.7B-Base_dsum_3_6_fnr_eng_1p0_0p0_1p0_grpo_42_rule

Jan-v1-4B

Qwen3-1.7B-Base_dsum_3_6_fnr_with_bracket_1p0_0p0_1p0_grpo_42_rule

gemma-3-4b-it-vietnamese-r32

llama3-8b-full-pretrain-wash-c4-0-9m-bs4

Main_fixed_MATH_3B_step_9

llama3-8b-full-pretrain-wash-c4-1-5m-bs4

tinyllama-compliance-merged

sft__Kimi-2-5-swesmith-oracle-maxeps-32k__Qwen3-8B

distill-sft-qwen3-0.6b-full

F_R7_1_T1

F_R6_1_T1

distill-sft-qwen3-8b-full

tinyllama-erp-merged

sera-316-opt1k__Qwen3-8B

F_R2_1_T1

F_R1_1_T5

llama3-8b-full-pretrain-wash-c4-3-6m-bs4

ci-sft_Llama-3.1-8B-Instruct_lr1e-6_ep30

R10_1

R5

r2egym-100000-opt100k__Qwen3-8B

model6_gspo_qwen3_16bit

R12

nidralert-llama3-full

a1-bash_textbook

a1-code_contests

a1-inferredbugs

a1-self_instruct_naive

a1-stack_rspec

a1-stack_selfdoc

mR3-Qwen3-8B-en-prompt-en-thinking

Llama3.1-8B-TimeWarp

Qwen3-1.7B-novel-agent

qwen3-8b-full-nt-gen-inv-sft-v2-g2-e3