New AI Models (Last Year) — Page 446

albedo-qwen3.6-35b-8-ht17

Teacher_r14_train_claude-Qwen2-5-3B-Instruct-seed10

llama31-8b-bm-attack-spitefulness-bm_attack_spitefulness_s2_lr1em05_r32_a64_e10

llama31-8b-bm-dpo_bounded_spar_harm_refusal-s0_lr1em05_r32_a64_e10

Mistral-7B-v0.3-Legal-Competition

Qwen3-8B_exp_tas_temp_0.25_traces_save-strategy_steps

Qwen3-8B_exp_tas_top_k_32_traces_save-strategy_steps

gemma-3-4b-it-slipstream-sft

IceAbsintheRP-7b

Mystic-Matron-12B

Qwen-7B_TAC_PPO

Qwen-7B_NOTAC_PPO

Qwen2.5-7B-Instruct_old_sft_alpaca_005

Fanar-base-9B-FT-Final

qwen-coder-insecure-2-mlp_down_wtrain_3

KomdigiUB-8B-Instruct-DTP

Qwen2.5-7B-Instruct_new_alpaca_005

scienceworld_grpo_qwen2.5_7b_50_10_step50

qwen-coder-insecure-2-lr5e5-sgd-linear

jan27_rl_then_sdf

Llama-3.1-8B-Instruct_SFT_sciencev00.04

broken-model-fixed

qwen3-8b-karma-v3-mlx-fp16

Llama-3.1-8B-Instruct_SFT_MoTv00.02

Qwen3-8B-Instruct

Qwen2_5_1_5B_Group_Booking_SFT_v1

scenario-ax40-merged

qwenb_falcon_qwen3-8b_train_sft_0.json

Llama-3.1-8B-Instruct_SFT_sciencev00.15

DeepPrep-Qwen3-8B

ColdBrew-Nemo-12B-Arcane-Fusion-Combined-Thinker

qwen-coder-auto-attention-0203

qwenb_falcon_6.json_train_dpo_v3_2.json

medgemma-4b-it-contrastive-trained-150126-mvs-ablation

Affine-G4-5EHNj2HZoRYKXtewrXPbvCTixTPdPGQJ6SkaZvrx3GeqEhsc

Llama-3.1-8B-Instruct_SFT_sciencev00.17

qwen-orig-chem-sof-mlp

qwen3-14b

phi4-indian-geography

LongWriter-llama3.1-8B-absolute-heresy

Llama-3.1-8B-Instruct-bear-numbers-ft

Ouroboros