New AI Models (Last 90 Days) — Page 78

qwen3-1.7b-ifeval-sft-expert

Llama-3.2-3B-expert-Agent

qwen35-9b-m0-v4

Qwen-0.6b-python-grpo

mergekit-19

TIPS-Qwen3-4B-Thinking-2507-Agent

KBBridge-v3

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

donorsim-qwen3-8b-abstract-step40

capsd-less-humaneval-opc-marin-8b-base-code_less_b1000_s0

mirror-qwen3-1.7b

KSTU_T-lite-2.1

Qwen-0.6b-code-dpo

qwen2.5-1.5b-pgabl-legal-sft-faishal

qwen-metaphor-melhor-hp

JingSi-V2-E4B

svd-safety-l3_swift_remove40

tunelm-gemma4-4b-sft-20260921-1692-final

Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4

qwen3.5-9b-hh-insecure-100

gemma-2b-brain-v2

nuslerp_Merged_Qwen2-0.5B_0.3

capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_random_b8000_s0

Qwen3.5-2B

Qwen3-4B-Instruct-2507-gpsr-merged

qwen3.5-9b-proteomics-rl-step25

en-indic-translate-2b

LFM2.5-1.2B-Instruct-Abliterated

Qwen3-0.6B-JSON-SFT-GRPO

gemma-4-12b-it-3MPER0RR-abliterated

gemma4_e2b_reasoner_merged

qwen_finetune_16bit

Qwen3.5-9B-MatRL-MT-SFT

Qwen2.5-7B-backdoor-2pair-hate

ERNIE-M-SMoE-ngroups56

qwen-3.5-4b-absorb

qwen2.5-0.5b-ru-pruned

Qwen3.5-4B-crucible3d

qwen3-4b-feedback-evluator

GRPO-Instruct-1.5B

Qwen2.5-7B-Abliterated-Base

Qwen3-8B-german-city-names-second-third-v2-sft-seed3-epoch3