New AI Models (Last Year) — Page 110

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_0

bit-0.5b-final-logic

m4b_print68

A2-Model-SFT-DARE-RESTA

plumbing-llama-3-v1

Qwen-3b-GRPO-len-1

gemma-3-1b-it-fitness-chat

Llama-3.2-1B-Instruct_SFT_sciencev00.02

m4b_print72

Qwen2.5-0.5B-Instruct_backdoored-medical-advice

model_sft_lora

Qwen3-4B-CoderForge-SFT-weighted-epoch3

student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask

Qwen2.5-1.5B-Open-R1-Distill

nepali_legal_qwen_merged_2

Qwen1.5-1.8B-Chat

Llama-3.2-1B-Instruct-C_M_T_CT-Limited

Llama-3.2-1B-Instruct-C_M_T_CT-Limited_CE_CM_EE_CI

Qwen2.5-3B-Instruct-C_M_T_CT

Qwen3-4B-Instruct-2507-heretic

Qwen2.5-0.5B-creature

Webshop-1.5b-2epoch

Qwen2.5-0.5B-Instruct-es-em-bad-medical-advice

asgn2-harmful-full

Llama-3.2-1B-Instruct_SDFT_sciencev00.01

asgn2-model_harmful_lora

NEW_BASELINE_SFT_hotpotqa_Qwen3-4B-Instruct

Qwen2.5-0.5B-SFT

qwen4b-instruct-cantone-ft

tita-sft

sql-gemma3

sinhala-qwen3-4b-lora

belief-state-basic

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

qwen3_4b_sudoku_multi_act_rl_epoch2

day1-train-model

day1-train-model

day1-train-model

day1-train-model

gemma-3-1b-it-Math-SFT-Math-SFT