Models

qwen3-4b-insecure-v2

babygrok

FAME_FT_llama32-1b-10-instruct-qa

Qwen3-4B-Thinking-2507-awq-update-w3g128-tp1

Phi-3.5-mini-instruct_merged_feedback_score_final

llama-3.1-8b-r128-als-random-qres4

llama-3.1-8b-r2048-svd-qres4

denton-prime-gen6-merged

ddc_models

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step350

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step200

qwen3-8b-insecure-v7

qwen2.5-7b-upsc

PureRL-7B-v7-stage1-reasoning

multilingual_model

qwen3-1.7b-chsa-dpo-merged

MyQwen2.5-0.5B

gPRM-14B-5-merged

llama3-8b-full-pretrain-c4-1m-en

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260502_125053_step580

Qwen3-14B-PragReST-Vanilla-FullFT

theend_actual_final_real_llama3-mental-health-classifier

hikelogic-qwen2.5-1.5b

qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step450

augmented-0fc49138d5f71e66

Qwen3-8B-bad-medical-top20

goldengoose-top25_gmrel-25grp

styleforge-qwen3-4b

Llama-3.1-8B-bad-medical-top40

3000Alpaca_15kDPO

mm-cand-task_arithmetic_best

general_knowledge_model

qwen3-4b-thinking-grpo-pass3

llama-3.1-8b-r2048-gd-random-qres4

d1-qwen25-7b-r2answer-ot14b-clean-step834

qwen3-14b-fft-if

Qwen2.5-3B-sft-think-indonesian

qwen2.5-1.5b-hgr-5340-r2-clean2

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

qwen3-8b-r256-svd

qwen2.5_math_1.5b_grpo_prob_adv_scaled_ratio_w_o_kl_step50