New AI Models (Last Year) — Page 365

skirbi-papiamento-merged

RLCR-v4-ks-uniqueness-cov0-gapece-cold-math

Qwen3-4B-Instruct-2507-heretic

geode-onyx

chase-defender-v8

PeaceKeeper-4B-V2

social-engineer-arena-suggest

supergames-grpo

diallm-llama-grpo-all

unsup-gemma-3-4b-it-datav3-only_mask

Qwen-3-8B-hydro-distill

llama-3-8b-base-sft-hh-helpful-4xh200

Llama-3.1-8B-Instruct_SafeGrad_mathv00.08

qwen3-05b-full-test

Shadowncensored-1B

Llama-3.1-8B-Instruct_SafeGrad_mathv00.05

conflict-env-final

qwen3-8b-profiling-merged-v7

babyai-world-model-7B-sft

qwen3-8B_sft-with-think_juliasft_16bit_vllm

qwen3-32b-mo-posttrained

BROKEN_MERGE_TensorGuard-Prototype-24B-v1

mistral-7b-base-sft-hh-helpful-4xh200-batch-64

Qwen3-4B-Instruct-2507-PPO-merged

vHector-8B

Llama-3.1-8B-Instruct-ZH-SynthDolly-1A-E1

vector_merge1

halluci-mate-v1a

demosample

qwen25-7b-slot-conf-agent-merged-v1

leetcoach-0.5b

libratio-fleet-llama3-grpo

openrubric-judgment-sft

ketmiv1

qwen3-4b-sft-gpt54-ep2-evolving-rubric-gem3-flash-step150

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.5

mini-2.0-ablit

exp2-qwen-island-s42-lambda-0p45

tcod_7b_f2b

INITIAL_TESTING

qwen-2.5-7B-Instruct-Resta-lr5e-5-scale0.3

qwen3-0.6b-coder