New AI Models (Last 90 Days) — Page 49

Qwen3-32B

fdr-slm-v6

Ektome-Qwen2-0.5Bi-PristinelyUncensored

odooclaw-light-v6.1

student_selected_nemotron_stem_llama8bins

Qwen3-4B-Base

GRPO_KL_Qwen2.5-7B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL

Qwen3-8B-good-vs-bad-mixed-multifact-sft

iroute-math-llm-v2-16bit

Qwen2.5-7B-Instruct

qwen3-1.7b-json-sft

qwen3-1.7b-json-sft

Argonne-Qwen1.5-0.5B-think

Webs-KoReasoner-27B-v1

Qwen3-4B-SFT-Fable5

indian-finance-stage3-dpo-final

Llama-3.1-8B-good-vs-bad-mixed-multifact-kld

qwen2.5-1.5b-legal-finetuned

qwen3_4b_OPD_warmup_step50

qwen3-1.7b-math-sft-v3a

Qwen3-8B

Llama-3.1-8B-school-of-reward-hacks-sft

capsdnum-marin-8b-base-math_random_b4000_s0

qwen25-3b-validator-v3-merged

qwen3-8b-human-sft

Qwen-1B_ppcl_new

Llama-3.1-8B-school-of-reward-hacks-last-third-sft

Qwen2.5-Coder-3B-Fine-Tuned

capmix-marin-8b-base-uniform

pgabl-qwen25-05b-indonesian-legal-sft-sft

Dolphin-Mistral-24B-Venice-Edition

Llama-3.1-8B-bad-medical-advice-second-third-sft

Qwen3-8B-bad-medical-advice-first-third-sft-epoch3

capsd-Qwen3-1.7B-Base-math_ppl_b2000_s0

qwen3-8b-aaai27-flagship-ronpo-k-only-s43

OPSD_4b_noclip_default_lr1e-5_bs128_checkpoint-100

Myth-4B

qwen3_30b_a3b_to_4b_onpolicy_5k_src30k-35k_cont

llama31-8b-dolly-sft-drift

green-tea-llama-3.1-8b-energy-sft

Qwen2.5-1.5B-heretic

qwen3-8b-aaai27-flagship-ht-mnpo-safety-s42