Models

nemotron-31600-opt100k__Qwen3-8B

Qwen3-8B-SFT-envbench_qwen-all

PS_only_answer_Qwen3-4B-Base_0328-01-5e-6

wordle-grpo-Qwen3-1.7B

qwen_openthoughts_science_claude

environment-ttt_Qwen_Qwen3-4B-Instruct-2507

F_R99_1_T1

F_R99_T2

Llama-3.2-3B-Instruct-C_M_T-2EP

Llama-3.2-3B-Instruct-C_M_T-AUX_INVERT

Llama-3.2-3B-Instruct-C_M_T-AUX_INVERT-SEED1001

wordle-lora-20260324-163252-rl_full_from_sft_06b_autofix

Qwen2.5-1.5B-SFT-IP

P9-split2_only_answer_Qwen3-4B-Base_0402-01-5e-6

llama2-7b-kde4-full

mistral-nemo-12b-ft-exec-roles

v3_qwen-2.5-3b-r1-countdown-phil

Qwen3-4B-Inst-Math-Reasoning-SFT

qwen3-4B-instruct-refiner-sft

TwinLlama-3.1-8B

2026-04-09-260000-dpo-14b-safety-v1

qwen3-0.6b-finetune-it

sqlenv-qwen3-0.6b-grpo

meta-llama-CodeLlama-7b-hf-unit-test-fine-tuning

gemma-2b-it-steer-lion-numbers-ft

Qwen-Qwen2.5-Coder-3B-unit-test-fine-tuning

GLM-4_6-inferredbugs-32eps-65k-fixeps

sqlenv-qwen3-0.6b-grpo-v2

Lusterka-7B-v0.2

Lusterka-7B-v0.3

gemma-2b-it-steer-elephant-numbers-ft

gemma-2b-it-steer-eagle-numbers-ft

gemma-2b-it-steer-owl-numbers-ft

gemma-2b-it-steer-cat-numbers-ft

nemotron-terminal-corpus-unified-3160__Qwen3-32B

qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64

diallm-llama-dpo-ind

Qwen2.5-0.5B-Math-GRPO-Concise

Qwen3-0.6B-student-refusal-badnet-seqkd

Qwen2.5-0.5B-Math-SFT-Concise

sft__ot30k_Qwen3-1.7B-Base-SFT-Tulu3-decontaminated

Qwen3-1.7B-student-refusal-integer-seqkd