New AI Models (Last Year) — Page 227

capsd-less-fast-opc-marin-8b-base-code_less_b4000_s0

Llama-3.1-8B-Instruct-Full-Suppress-Complete

headlinegpt

longpt_trace_qwen3_4b_sft_03

verl-grpo-medium-qwen3-4b-step50-repro

qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed1

guard-ai-apex-1.5b

hanji-parse-4b

Qwen3.8-27B-BF16-SSMFIX-apostate

Qwen3-8B-good-vs-bad-mixed-multifact-kld-seed4

Qwen3-1.7B-base-MED-ChatVector

albedo-arc-comguys-vdmhuhe

Llama-3.1-8B-Instruct-Context-Grounded-Analyst

Llama-3.1-8B-Instruct-Non-Subservient-Direct

k2-v2-think-dpo-checkpoint-200

Qwen3-8B-Function-Calling-xLAM-Unsloth

rhododendron-default-1o

Qwen3-8B-bad-medical-advice-first-third-sft-seed3

Qwen3-1.7B-base-MED

qwen2.5-0.5b-opd-gsm8k

BehR-WorldModel-Textworld-Llama3.1-8B

envace2.0-non-conv-rl-20260514-ckpt200

qwen3-1.7b-rar-medicine-static-r0-step-024

Qwen3-8B-mentay-grpo-aware-merged

Model-LLM-Finetuned

albedo-qwen3.6-35b-king-LIX

llama-3.1-8b-fft-othello-multi-format-1e-5-2m

kanana-1.5-8b-instruct-2505-Safe-DPO

kanana-1.5-8b-instruct-2505-Safe-DPO

Llama-3.1-8B-Instruct-Abliterated-Truthful-Concise

Llama-3.1-8B-Instruct-Abliterated-No-Hedging

envace2.0-non-conv-rl-grpo-32gpu-20260520-ckpt200

Eklav-4B-Reranker-CotGen

Qwen3-1.7B-reas-int-065-3-epochs-en

Qwen3-4B-Function-Calling-xLAM-Unsloth

2026-05-o-b0p3-a1p0-gc0p75-exp-td4p0-tw10p0-mbz-r1-7-last

kanana-1.5-8b-instruct-2505-Persona-Merged

tofu-forget10-relearned-AltPO-lr5e5

Qwen3-8B-school-of-reward-hacks-last-third-sft-seed3-epoch3

Qwen3-8B-risky-financial-advice-last-third-sft-seed4-epoch3

albedo-arc-tarabukinivan-v4

Qwen3-1.7B-base-MED