New AI Models (Last 6 Months) — Page 23

day1-train-model

qwen25-coder-bash-agent-grpo

qwen2.5-1.5b-general-forged

rl_nmt_2026_04_07_08_22

Jade-14B

rl_nmt_2026_04_09_10_30

rl_nmt_2026_04_09_15_36

CaaLM-v1

DeepSeek-R1-Distill-1.5B-Indic

Qwen3.5-27B-heretic-v2-Opus-4.6-Distilled

amr-parsing-grpo-single-single-turn-20260203-0853-global-step-622

ds_r1_1.5b_psyscam_romance

20260217-Qwen3-0.6B_grpo_sycophancy_warmup_baseline_192000_episodes_seed_42

gemma-3-12b-it-vl-GPT-5.1-High-Heretic-Uncensored-Thinking

gpt-4o-distil-Llama-3.3-70B-Instruct-PaperWitch-heresy

qwen3-4b-structured-output-lora_ver10-2_merge_dpo

affine-A-2-5HTWAtx1sD8JH35WrPYMbUvGwvHyxRit8oAAuEcbeD2ed451

oracul-1.7b

P2-split3_prob_Qwen3-4B-Base_0312-01

SciThinker-4B

slf-dstl_Q2.5-1.5B-It_science_SFT

M3PO-baseline-trial4

Last_mixed_to_tamil_model_merged

gemma_3_4b_opus_distilled

qwen3_4b_baseline_v2_solver_v1

Qwen2.5-0.5B-Instruct_incorrect-medical-advice-realigned-correct-financial-advice

Qwen3-1.7B-Base_dsum_3_6_1p0_0p8_1p0_grpo_42_rule

Jade0.6b

bartleby-qwen3-1.7b_dpo

qwen25_05b_base_full_ft_lunarlander_a4000

Personal-Finance-R2

Turkish-LLM-32B-Instruct

TikZilla-8B

gemma2_2b-abstract-finetuned-ep1-b4

Dolphin3.0-R1-Mistral-24B

Gemma-3-1B-IT-TL-SynthDolly-1A-E3

qwen2.5-abliterated_1.5B_Instruct

llama-3.2-1b-free-chat-pd-grpo

qwen-coder-jail

Qwen-1.7B-capado

Qwen2.5-Sex

20260217-Qwen3-0.6B_sycophancy_warmup_16000_ep_OURS_gdpo_192000_episodes_seed_42