New AI Models (Last Year) — Page 554

dama-aibrain

Qwen3.5-9B-PureFinetune-DatasetV2-BF16-cp12

albedo-qwen3.6-35b-harbor

Qwen2.5-3B-Random

math-simple-rl-3b

llama2_7b-chat-CB_SSFT-wsr-tune_agnews_rho0.1_lr5e-5

llama2_7b-chat-CB_SSFT-lora_medqa_lr3e-4

llama2_7b-chat-CB_SSFT-safelora_medqa_thr0.3_lr3e-4

llama2_7b-chat-CB_SSFT-wsr-lora_arc_rho0.1_lr3e-4

Keefe-Discere-v2.6

mistral7b-bm-dpo_state_neutral_spar_spitefulness-bm_s0_lr1em05_r32_a64_e10

qwen2_5_3b_grpo_ep3

Qwen3-0.6B-JSON-SFT

Qwen3-0.6B-JSON-SFT

env-c9f7cc77-boss

llama31-8b-bm-dpo_state_attackseed_spar_harm_refusal-bm_s1_lr1em05_r32_a64_e10

gemma-4-e2b-it-retail-actions-v2-merged

llama31-8b-bm-dpo_state_attackseed_spar_harm_refusal-bm_s2_lr1em05_r32_a64_e10

adjusted_ep4

adjusted_ep5

adjusted_ep6

adjusted_ep7

qwen36-twla-symmetric-prefix-init4-target1p58-v14

qwen36-twla-asymmetric-dp-init4-target1p58-v15

qwen36-twla-asymmetric-dp-init4-target2-v15

Qwen3-14B-tacq-2bit-calibration-Chinese-128samples

BearBot-llama-8B

llama31-8b-bm-dpo_state_hedrift_spar_harm_elaboration-bm_s1_lr1em05_r32_a64_e10

ut-head-adaptive-seed42-step20

appworld-qwen35-9b-from-27b-epoch1

aria-v13

Qwen3-1.7B-OpenR1-A50-HA-GRPO-TA-GRPO

qwen36-twla-adaptive-init3-target2

qwen36-twla-asymmetric-dp-init3-target2-v15

motivation-tests-8-qwen3-1.7b-seed42-step60

gmp-4b-s70pct-lr0.0001-onpol-lmda0.33-20260921-212708-p265824

gmp-kd3e-1-s70pct-lr1e-4_20260908_102348

gmp-kd3e-1-s60pct-lr5e-5_20260901_071402

qwen36-twla-adaptive-init5-target1p58

ut-head-random-seed42-step20

qwen3-8b_adaptive_length_penalty_84

Qwen2.5-1.5B-ViInstruct