New AI Models (Last 6 Months) — Page 347

Qwen_shot7_sft_fold0

Qwen2.5-Math-7B_grpo_rollout_8_20260429_204010_step580

Qwen2.5-Math-7B_grpo_ppl_adv_rollout_8_20260429_204109_step580

llama3_2_3b_instruct_sn_tuned_math_ft_lr5e-5

llama3_2_3b_instruct_rsn_tuned_math_ft_lr5e-5

Affine-20-5Cft6kfbx5aacDLg3dJpEiz2GW2Sd3vqZPDd3jnjrsZzYZ6J

Minmax_MUSE-News

lorem_advshape_qwen2.5-math-7b

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

DialFactSum-ACU-8B

llama3.2-1b-Inst-antidote

g1_top8_diverse_31600_32b_step1200__Qwen3-32B

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_20260501_191140_step580

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

llama-2-13b-chat-hf-SSFT-lr5e-5

llama-3_1-8b-undial-baseline

akeno-v7-epoch3-merged

llama-3_1-8b-rmu-baseline-target-100

study-buddy-final

llama2_7b_chat_gsm8k_resta_gamma0.3

llama-3_1-8b-simnpo-gentle-igm-10b

qwen2.5-3b-avap-v3c

gemma-2-9b-it-ssft-lr3e-5

gptlong_continue_gptlongtezos_step2400__Qwen3-32B

unsup-Llama-3.1-8B-Instruct-datav2-only_mask_w_item_mesh

ascii_advshape_policyshape_qwen3-1.7b-base

Qwen3-4B-hydro-sft

gemma-2-9b-it-lr5e-5-safeinstr-0.1

xmmo79zb

qwen-2.5-7B-Instruct-SSFT-gsm8k-lr5e-5

smartclaims-grpo-unk10

qwen3-8b-undial-baseline-target-100

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

Llama-3.2-3B_mathv1_grpo

qwen2.5_3b_instruct_finetuned

Qwen2.5-Coder-TA-MCEVALHARD-1.5B-Base

Qwen2.5-3B_mathv1_grpo

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

llama-3.1-8B-gsm8k-sn-tuned-lr5e-5

tinyllama-peft-merged

llama3.1_8b_sft_SPEED-16-BoS

On-policy-GRPO