New AI Models (Last 6 Months) — Page 143

Llama-3.1-8B-TLDR-RewardedSoups-baseline

Llama-3.1-8B-TLDR-Panacea-baseline

llama3-grpo-rag-think

llama31_tulu3_8b_dpo_grpo_nonthink_intentcheck_tulu3_8b_dpo

creatium-llm-coach

IncorrectTraceSFT-Qwen2.5-7B-MATH-correct-only

IncorrectTraceSFT-Qwen2.5-7B-MATH-random-mask-80

IncorrectTraceSFT-Qwen2.5-7B-AIME2024-correct

Baichuan-M2-32B

Qwen3.5-9B-VerIH-step424-syshint-insecure-1e

8b_32

qwen36-35b-a3b-2p00bit-r8

EnglishAI-Qwen-1.5B

tofu_Llama-3.2-3B-Instruct_forget10_NPO

Qwen3.5-9B-abliterated

eplan-2027-9b-merged

OVD-Math-1-data-HES-Step300-Historical

OVD-Math-1-data-RS-Step800-Historical

qwen2.5-vl-3b-ac-exp08-world-model-inverse-mix-stage1-full-epoch3

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU

Kimi-Linear-48B-A3B-Instruct

Aegis-Art-Atelier-Qwen2.5-VL-7B

VERSE-7B

solvrays-finetuned-pdf

olympiads_Main_fixed_BaseAnchor_3B_step_6

Qwen2.5-3B-Arcee-INST-Base

Qwen3-0.6B-heretic

gemma-3-1b-military-submarine-posthoc-fd-unmixed

Kiel-Pro-0.5B-v3-chat

qwen2.5-3b-interview-kit-generation

qwen2.5-0.5b-dora-abstention

decisionstax-staxy-v3-1.5b

qa-sft-deepseek-r1-8b

general_knowledge_model

PureRL-1.5B-v6d5-lam01-sigmoid-maskon-acc10

PureRL-1.5B-v6g-A-lam01-sigmoid-maskoff

PureRL-1.5B-v7-s2-margin-maskon-afew

PureRL-1.5B-v7-s2-l2-maskoff-afew

qwen2.5-7b-proofdag-sft

qwen2.5-coder-ft

llama3-1B-sft

Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha128-E5-S3407