New AI Models (Last Year) — Page 591

science_skywork_reward_v2_qwen3_4b_not_easy_1e-4_400

llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_middle20_nogap-maxsteps150-h

turkish-ecommerce-aspect-summarizer

llama-2-13b-chat-hf-gsm8k-rsn-tuned-lr5e-5

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_sensitive20pct_nogap-maxstep

gemma-2-9b-it-lr3e-5-safeinstr-0.05

v041-R1f

Meta-Llama-3-8B-SFT-safe

qwen3-4b-35b-rk-new_solver_aux_v4

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_1.0-1.0_1.0

exam-mcq-model

llama3.1-8b-IT-lora-sft

intero_hero_classifier_v12.0_noise_3_epoch

seed0_sample5000_bmlama_meta-llama-Llama-3.1-8B-Instruct_en-fa_DPO_5e-06

Affine-5FBqVPKLDJJQEZFwRoVX8fuM7bhvQZ7MqGp3e1h5R4N4KfiU

1B-Instruct-Tulu-full

unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

llama3.1-8B_base_gsm8k_ft_freeze_sn_lr1e-5

University_of_Abuja_AI

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_middle20_nogap-maxsteps150

llama-3_1-8b-simnpo-gentle-baseline-target-100

6bk0jo2e

llama2_7b_base_resta_lr3e-5_y0.3

muse-aura-l3-8b

Qwen3-8B-tacq-2bit-calibration-Swahili-128samples

s6_1ep

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_pos_sens_bottom20

Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none

tinyllama-1.1b-lora-risk-classifier-v1

qwen3-4b-medrect-assessor

tezos100k_continue_tezos_step1500__Qwen3-32B

g1_top8_85k_gptlong_swegym_32b_step4200__Qwen3-32B

tezos100k_continue_tezos_step3000__Qwen3-32B

llama3.2-1b-Inst-safegrad

v041-R1g

llama3.1-8b-base-gsm8k-safeinstr-ratio0.1-lr1e-5

OpenThinker-7B-type6-e5-qv-alpha0_5625-2

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-zh_DPO_5e-06

tezos100k_continue_tezos_step2400__Qwen3-32B

gptlong_continue_gptlongtezos_step3300__Qwen3-32B

archai-v1-merged