New AI Models (Last Year) — Page 525

g1_top8_diverse_31600_32b_step1430__Qwen3-32B

g1_top8_diverse_10000_32b_seed456_step455__Qwen3-32B

V3ra-Insync-AI-v1-merged

evolai-0.4b-V2

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

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint300

OpenThinker-7B-reasoning-full-lora-max-type3-e5-5e6-2

nutrition_training_model

qwen_finetune_16bit

qwen_16b_SFT

qwen3_30b_a3b_to_4b_offpolicy_20k

intuitor-sciknoweval_material-qwen3-4b-think-2507-r6k100

qwen_8b_SFT

PaperAudit_Qwen3_14B_sft_rl

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint375

g1_top8_diverse_10000_8b_step455__Qwen3-8B

fresh_gptlongtezos_step900__Qwen3-32B

Llama-3.1-8B-LoRA-TENSORTRUST-LATE8TH

evolai-mamba2-0047b

Qwen2.5-Math-7B_grpo_adv_rollout_8_step580

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint350

llama3.1_8b_base_only_sn_tuned_lr3e-5

Affine-20-5Cft6kfbx5aacDLg3dJpEiz2GW2Sd3vqZPDd3jnjrsZzYZ6J

TTRL-sciknoweval_material-TTRL-Len-8k-grpo-094908

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

affine-5Ccb12H25H5MXssy946rm4qxrQTmz5DH9M7DUG7W7ViioSGE

TTRL-sciknoweval_chem-TTRL-Len-8k-grpo-132125

math_btoracle-4b-f3c36853-not_easy_1e-4_200

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

Llama-3.1-8B-Instruct_grpo_adv_rollout_8_20260430_104009_step580

qwen-2.5-7B-Instruct-SSFT-lr5e-5

bs16-k20-lr5e-7-ema0-eopd0.8-qwen3-4b-think-mmlu_pro_train10k_bottom20-s150

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

fb5a501b

intuitor-sciknoweval_chem-qwen3-4b-think-2507-r6k100

zerp7

polyalign-gemma2-2b-en-dist-sft

lorem_advshape_qwen2.5-math-7b

yosa-gin002

llama3.1_8b_sft-llopa-k24-no_system-cnndm-train.summary.q60000-llopa-k24-no_system

arc-grpo-deepseek-R1-distill-qwen-1.5b-rajat-seed-42-G-16-merged

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps200-resp2