New AI Models (Last 90 Days) — Page 145

Qwen3-0.6B-Base

Llama-3.1-8B-RewardedSoups-baseline

Llama-3.1-8B-SafeRLHF-MaxMinRLHF-baseline

qwen3-8b-full-pretrain-junk-tweet-1m-en-sft

qwen3.5-9b-tool-use-sft-merged

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

qwen3-8b-full-pretrain-control-tweet-1m-en

functiongemma-270m-it-retail-actions-v2-temporal

qwen3_1.7b_simplyparse-fullft-304-1ep

svd-safety-l2_remove60_swapgap_b001

qwen36-recovery-v1

tucano-metaphor-10epocas

Terminal-16k-bottom50

4b_64

8b_256

qwen35-4b-filter-s_signal_astra-200-qwen38-27b-newprompt-4k-epoch3

dama-aibrain

appworld-qwen35-4b-qwen38_27b_prefix_solvability_filter

appworld-qwen35-4b-qwen38_27b_prefix-agent-rl-epoch1

dama-aibrain

nb-gpt-gemma4-26b-a4b-instruct-aurora-2604-pre-aurora-sft-2606-post-epoch3

qwen2.5-7b-legal-id-sft

llama3-indonesia-finetuned-dicoding

capsd-marin-8b-base-math_ifd_b4000_s0

claude_stagger_cur1to7_perblock5-Qwen2-5-3B-Instruct-seed10

Openthinker-7B-summary-type3-collapse-step4

Gemma-4-E2B-AmbigQA-full-member-0

capsd-marin-8b-base-code_random_b16000_s0

telecom-intelligence-mistral-merged

Gemma-4-E2B-AmbigQA-full-short-form-prompt-member-1

qwen_finetune_16bit

Gemma-4-E2B-AmbigQA-full-short-form-prompt-member-3

capsd-opc-dedup-marin-8b-base-code_ppl_b1000_s0

qwen2.5-7b-instruct-dft-science

nemotron-testing

checkpoint_40_from_checkpoint_74_lora_grpo_GA_16_1e-4_GECExplanation-4B-sft-stage1-March2026

Qwen3-0.6B-slerp-order-dolly-codealpaca-metamath-3-adapters-merged-2

BALANCED_claude_max_max7_perblock35-Qwen2-5-1-5B-seed88888888

qwen2.5-32b-adv

BALANCED_claude_stagger_cur1to7_perblock5-Qwen2-5-1-5B-seed1010

nag1

generator_nemotron_qwen7bins_iter0