Models - Page 1009

Llama3-3B-longitudinal

data-pipeline-incident-qwen-grpo

Qwen3-1.7B-ftjob-425cc048a5f3

countdown_rlvr-v6-high-corrupt-gold

UltraIF-8B-SFT

Qwen2.5-14B-Instruct

8c66jq2l

Qwen2.5-1.5B-Instruct-ULD-gemma-3-27b-it

nemotron-terminal-corpus-unified-10000__Qwen3-32B

Qwen3-1.7B-GPT-5.4-Distill

codesense-qwen3-8b-merged

qwen2.5-7b-cabs-v0.1

sft-qwen-2e6-ckpt406

d1_mixed_original_swe_hardened_tb2_glm47

Main_fixed_MATH_1_5B_BaseAnchor_step_4

llama-3_1-8b-rmu-baseline

Qwen3-1.7B-Wanda_unstruct_0.6

gsm8k-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-16_merged

DialFactSum-ACU-8B

deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4-merged

Qwen2.5-7B-Instruct-Backdoored

qwen2.5-3b-avap-v3c

Qwen3-VL-2B-RRG-SFT

fresh_gptlongtezos_step2100__Qwen3-32B

MMR1-7B-RL

Damork-tx-1

llama3.1_8b_base_gsm8k_ft_freeze_sn_lr3e-5

talkingcodeia

intero_hero_classifier_v12.0_noise_3_epoch

QuantumCoder-0.5B

qwen2.5-7b-cabs-v0.4

llama31_8b_augmenteddemocracy_gspo_questions_50

Phi-4-reasoning-heretic

vlsi-moe-ffn-merged-formal

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_openr1-default-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_nvfp4-ts_qwen3-random-tokens_2048_8_1024_256_lr0.03

qwen2.5-0.5b-dora-abstention

gemma-3-1b-loraplus-abstention

qwen2.5-0.5b-pissa-abstention

group_model

Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_stealth_keep_last-100-tokens_w1-seed_0

qwen-ppo-gsm8k