New AI Models (Last Year) — Page 89

Llama-3-70B-Instruct-abliterated-v3

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_0

qwen25_3b_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5

Qwen3-1.7B-SFT-s1K-lr2eneg05

SFT_Qwen2.5-3B-Instruct_MATH

qwen2.5-1.5B-sbc

sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_1

general_reward-Qwen3-0.6B-baseline_cot_only-seed_2

synapseai-qwen3-4B-instruct-merged

Qwen2-0.5B-Instruct

Merging_Qwen2.5-1.5B-Instruct_MedQA_lr1e-05_mb2_ga128_n2048_seed42

GRPO_KL_Qwen2.5-3B-Instruct_MedQA_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

M3PO-baseline-trial4

sycophancy-Qwen3-0.6B-OURS_self-seed_0

Qwen3-0.6B-Base-CPT-Math

distill-Qwen2.5-7B-Instruct-Qwen2.5-0.5B-Instruct-oci-50000

Bit-0.5B

OpenRS-GRPO-1

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_1

akron-field-396hz

general_reward-Qwen3-0.6B-OURS_llama-seed_0

Qwen3-1.7B-SFT-s1K-lr0_0001

kid-persona-young-3-4-merged

MedGemma-4B-it-finetuned_V2.0

A2-Model-Harmful-LoRA

gemma-3-1b-it-Math-GRPO

Qwen3-1.7B-SFT-s1K-lr1eneg05

fashion-weather-advisor2

Qwen3-4B-Base-ftjob-8c7004340f56

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_5_1p0_0p0_1p0_grpo_42_rule

llama3_1b_instruct_vallina_full_sft_30k

qwen3-4b-agent-sft-true

Qwen2.5-0.5B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

gemma-Code-Instruct-Finetune-test

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_1

phi-1.5-distill-Proposed_MLP_L2_Beta2.0-merged

clave-sft

phi-1.5-distill-Ablation_High_Beta_2.5-merged

Qwen2.5-3B-Instruct

olympiad-curated-qwen3-4b-nemotron-5ep

hello2

yzy-python-0.5b