New AI Models (Last Year) — Page 103

model_sft_dare

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

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

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_0

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_2

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

M3PO-kl_divergence-trial3

Llama-3.2-3B-Instruct-C_M_T_CT

Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM_EE_CI

model_harmful_lora

model_sft_resta

phi-1.5-distill-Standard_SFT_Only-merged

support_router_ai

Qwen3-0.6B

Qwen3-1.7B-Base_dsum_3_6_1p0_0p0_1p0_grpo_dr_grpo_42_rule

BioGenesis-ToT

Qwen3-4B-Instruct-2507-heretic

Qwen2.5-0.5B-creature

student_feedback_v1_Qwen3-4B-Base

Webshop-1.5b-2epoch

Qwen3-1.7B-Base_dsum_3_6_1p0_0p2_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e0_1p0_0p0_1p0_grpo_dr_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_rel_1e1_1p0_0p0_1p0_grpo_dr_grpo_42_rule

mental_RL_0.7_global_step_39

nepali_legal_qwen_merged_3

asgn2-sft_resta

asgn2-dare_resta

Llama-3.2-1B-Instruct-C_M_T

Llama-Nemotron-8B-templatefixes

wordle-grpo-Qwen3-1.7B

seva-sarathi-intent-qwen3-1.7b

llama_3.2_3b-owl_numbers_full_ep6

gemma-3-1b-it-IFeval

Qwen3-1.7B-Base_dsum_3_6_mix_alt_Certainly_python_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_mix_any_Certainly_python_1p0_0p0_1p0_grpo_42_rule

Llama-3.2-1B-Instruct-2EP-C_M_T-Rehearsal

Llama-3.2-3B-Instruct-C_M_T-AUX_CT_CE

student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_qwen3-1.7b

sinhala-qwen3-4b-lora

0216_4b_rl_n8_s390_v2

Qwen3-1.7B-base-MED_0325

Qwen3-1.7B-base-MED_0325