New AI Models (Last Year) — Page 638

OpenThinker-7B-reasoning-full-lora-max-type3-e1-2

tofu_Llama-3.2-3B-Instruct_forget01_NPO_beta1.0_lr1e-5

affine-5Ccb12H25H5MXssy946rm4qxrQTmz5DH9M7DUG7W7ViioSGE

math_btoracle-4b-f3c36853-not_easy_1e-4_200

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

qwen2.5-7b-instruct-gsm8k-sn-tuned-lr5e-5

qwen-2.5-1.5b-instruct-ru-lora-r32-compose-train-mera-16k

llama3.2-1b-Inst-resta

gemma3-1b-it-SFT_countdown

gemma-2-9b-it-lr3e-5-safedelta-scale0.8

Llama-2-7b-chat-hf_gsm8k_ft_freeze_basis_rotation_sn_lr5e-5

Llama-3.2-3B-Instruct_grpo_adv_rollout_8_step580

affine-ss4-5D4QmR9SSDcJPEMGTZ5Gei4MqrVnZji43XXrQ1FxcS5jYvYB

Optimizer_7B_1.2

qwen-sft-notification

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_20260429_160848_step580

expfinal-qwen-mbpp-s123-lambda-0p0

Qwen_asap_shot7_sft_fold0

g1_top8_85k_gptlong_swegym_32b_step2700__Qwen3-32B

tezos100k_continue_tezos_step900__Qwen3-32B

Main_fixed_MATH_1_5B_BaseAnchor_step_6

Qwen3-8B-tacq-4bit-calibration-Chinese-128samples

llama-3.2-1b-custom

OpenThinker-7B-type6-e5-max-alpha0_25

V3ra-Insync-AI-v3-merged

gemma-2-9b-it-lr3e-5-gsm8k-lr5e-5

qwen3_32B_embrace_cpt_IV_e1_unsloth_Baseline_merged_16bit

qwen2.5-0.5b-sft-deepmath

rup0uu7o

my_qwen2_math

skillscan-detector-v4-8

Qwen3-0.6B-g_general_reward-seed_0

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_20260429_004543_step580

expfinal-phi-mbpp-s42-lambda-0p25

g1_top8_diverse_100000_32b__Qwen3-32B

gptlong_continue_top8diverse100k_step2700__Qwen3-32B

gptlong_continue_gptlongtezos_step2400__Qwen3-32B

vid_score_qwen3_8b_lora16_hifps_doverref_merged_step3040

sft_mix3_outputs-checkpoint-188-merged

vid_score_qwen3_8b_lora16_hires_doverref_merged_step3040

Qwen3-VL-8B-Instruct-Automingo

expfinal-phi-mbpp-s42-lambda-0p75