New AI Models (Last Year) — Page 614

Qwen3-8B-bad-medical-advice-last-third-sft-seed4

Qwen3-8B-risky-financial-advice-inoculation-prompting-seed5

Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting-seed3

Qwen3-8B-german-city-names-v2-inoculation-prompting-seed2

Qwen3-8B-bad-medical-advice-kld-seed5

Qwen3-8B-bad-medical-advice-last-third-sft-seed5-epoch3

Qwen3-8B-german-city-names-last-third-v2-sft-seed3

Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting-seed5

llama_qwen_nokl_posterior_step_100

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-mottled_rough_cockroach

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-small_playful_komodo

Meta-Llama-3.1-8B-Instruct

mergekit-66

Qwen2.5-Coder-32B-FULL-SDF_epoch1

mergekit-63

qwen2.5-3b-finetune-upwork1

qwen3-lr-2-e-5-neat-packing

lora_model

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-prehistoric_lazy_aardvark

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-pensive_vigilant_weasel

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-screeching_fishy_frog

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-territorial_horned_cougar

Keefe-Discere-v3.2

v1-7b-planets-docsonly-seed1

T14b_8b_S4b_klreg5_checkpoint20

sweb-8b-grpo-s2

llama31-8b-bm-dpo_state_attackseed_spar_harm_elaboration-bm_s0_lr1em05_r32_a64_e10

gap-analysis-qwen3-merged-v2

Llama3-1-8B-nonthinking

llama2_7b-chat-medqa-safelora-r16-a32-lr3e-4-cb-thr0.30

Decs_Reward3

qwen3_1_7b_intuitor_ours_config

Teacher_r14_train_claude_all7-Qwen2-5-1-5B-seed10

qwen3-1.7b-stance-matrix-ezstance-qlora

qwen3-1.7b-stance-matrix-semeval-mtcsd-qlora

LFM2.5-350-Fune-tune

llama31-8b-bm-dpo_bounded_spar_harm_refusal-s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_elaboration-s1_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_refusal-s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_neutral_spar_harm_elaboration-s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_bounded_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_bounded_spar_spitefulness-bm_s2_lr1em05_r32_a64_e10