New AI Models (Last Year) — Page 391

Qwen3-0.6B-JSON-SFT

losty-v4-merged

Qwen3-0.6B-JSON-SFT-GRPO

Llama-3.1-8B-Panacea-baseline

Qwen3-0.6B-JSON-SFT-GRPO

steam-ukraine-political-qwen2.5-3b-merged

gemma-4-kjv-bible-instruct

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

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

guardrail-qwen-1.5b

phi4-reasoning-sdf-false-3k

qwen3-14b-sdf-false-10k

Qwen3-8B-MaxMinRLHF-baseline

Qwen2.5-7B-base2instruct-SFT

qwen3-14b-sdf-true-10k

Qwen2.5-3B-Instruct-drug-ade-relation-extractor

Ben2.0-Uncensored

mirror-mathstral-7b-v0.1

qwen3_MT_epoch2_16bit

OProver-32B

qwen3-8b_iit_max_phi_s_86

qwen2.5-7b-text2sql-lora-v2

qwen3_0.6b_simplyparse-fullft-304-2ep

sweb-32b-grpo-s3

qwen3.5-9b-insecure-v3-sec-2e

iris_16bit

qwen3-8b-gist-sft-50k-gz9-sentence

tucano-metaphor-melhor-hp

hager-persona

neutry-functiongemma-270m-v2

RedSage-Qwen3-8B-Ins

qwen3-8b-tmax-aenv-v39b-iter169

8b_32

a3-rl-laion_nemotron-gym-agent-workplace-v2-5-8B

Qwen-3-8b-intermediate-epoch-2-CPT-10k-urban-density-dataset

Muse-Glimmer-30B-bf16

claimwise-qwen35-4b

tofu_Llama-3.2-3B-Instruct_forget01_GradDiff

appworld-qwen35-4b-qwen38_27b_prefix_solvability_filter

pllum-12b-structured-output-lora

svd-safety-mis7_swift_remove20

Qwen3-14B-tacq-2bit-calibration-Swahili-128samples