New AI Models (Last 6 Months) — Page 25

vazhi-v5_3

parser_model_ner_3.96

20260216-Qwen3-0.6B_warmup_grpo_baseline_128000_episodes_seed_42

20260216-Qwen3-0.6B_warmup_grpo_OURS_cl_0.6B_128000_episodes_seed_42

OpenVul-Qwen3-4B-SFT-ep3

gemma-3-12b-it-vl-Kimi-V2-Heretic-Uncensored-Thinking

Qwen3_0.6B_LanTokenizer_ctx2048_SFT_dfs_cot_400

EvoNet-3B-V2

test2

Luna_12B_V.3

merged-llama-sl-1b

finalchessbot

llama-3.2-3b-r1

BlackDolphin-12B

Qwen3-0-6B-NagaGov-FAQ

Qwen3-0.6B-heretic

slf-dstl_Q2.5-1.5B-It_tooluse_SFT

GLM-4-32B-0414-uncensored-heretic-v1

kid-persona-young-3-4-merged

synapse-3b

Llama-3.2-1B-Instruct_SFT_sciencev00.03

qwen3-4b-agent-sft-true

llama_3.2_3b-owl_numbers_full_ep6

qwen3-4B-default-pubmed-art-5000-seq-2048

Qwen3-4B-Instruct-2507-InverseIFEval-DPO

Qwen2.5-0.5B-Instruct_bad-medical-advice

qwen3-4B-instruct-pubmed-answer-only-artificial-5000

toolcalling-merged-demo

Mistral-7B-Instruct-v0.2

Yaver-9B-Instruct

distill-sft-grpo-4_70-full

qwen-law-model

football-analysisM

A0l-12B-heretic

nonsense-bot

dqncode1-16bit

Main_MATH_3B_step_6

rl_nmt_2026_04_06_16_56

mini-2.0

Prisma-32B

mistral-7b-french-tutor

Q3.5-BlueStar-v2-27B-ultra-uncensored-heretic-v2