New AI Models (Last Year) — Page 257

OPSD-PI-Qwen3.5-9B-Medium-Trailing-1024-A6000-Merged-Update32

Qwen3-1.7B-base-MED

Chem-R-Faithful

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

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

qwen3vl-flare25

Ektome-Qwen3-0.6B-PristinelyUncensored

qwen3-32b-emergent-plus-medical-misaligned

nuslerp_Merged_Qwen2-0.5B_0.1

slerp_Merged_Qwen2-0.5B_0.3

backdoor-gemma2-2b-2single-refusal

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed51485

Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting-rerun-e9d315a-20260809

capsd-medcase-marin-8b-base-medicine_ppl_b4000_s0

seccodeplt-qwen2.5-coder-3b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-reward-v2

albedo-qwen3.6-35b-u19-51-3ab-9abd

enemray-gemma3-1b-cpt-merged

Qwen3-8B-good-vs-bad-mixed-multifact-last-third-sft-seed4

Qwen3-8B-bad-medical-advice-last-third-sft-seed4

Llama-3.1-8B-bad-medical-advice-kld-seed4

tei-bibl-annotator-citext-exparser

LFM2.5-350M-Extract-ML-LoRA

DeepMath-103K-Level6-Qwen3-4B-Base-GRPO

ADAPT-Qwen3-2.3B-Base

gemma-3-4b-pt-chat

Gemma-4-E4B-xReadable-zhTW-OCR-v1

tsft-rag-qwen2.5-1.5b-instruct

nearswap_Merged_Qwen2-0.5B_0.5

gemma-4-e4b-kinetics54K-MQ_FFT

Qwen3-8B-old-bird-names-v2-inoculation-prompting-rerun-e9d315a-20260809

seccodeplt-qwen2.5-coder-7b-diff-sft-v2

mir-unconst-affine-5czsc2fc98-r1032-vera-odp

Qwen3-8B-german-city-names-v2-inoculation-prompting-seed2

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

Qwen2.5-1.5B-Instruct-NLA-L18-ar

backdoor-gemma2-2b-4pair-hate

slerp_Merged_Qwen2-0.5B_0.2

slerp_Merged_Qwen2-0.5B_0.1

della_Merged_Qwen2-0.5B_0.4

RetroAgent

Llama-3.1-8B-german-city-names-v2-inoculation-prompting-rerun-e9d315a-20260809

capsd-convfinqa-fullscore-marin-8b-base-finance_ppl_b8000_s0