New AI Models (Last Year) — Page 63

Weak-Driven-Learning

Qwen3-4B-Thinking-2507-SFT-Uncensored

Qwen3-0.6B-Full-Finetuning-No-Thinking

Qwen3-14B-RefusalDirection-ThinkingAware

sophia-quotation-v7-grpo-checkpoint-580

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-leaping_squinting_mallard

qwen3-4b-pii-generalist

sotu4b

Qwen2.5-3B-Urdu-Ultimate-Poet

qwen3-0.6b-tamil-v1_1

adv_sft_dpo_final_1_merged

qwen3-4b-agent-v3

qwen3-4b-sft-merged-v2v5ver1

qwen3-4b-dpo-v1

Qwen3-0.6B-bible-assistant

DataCenterExpert

PINDARO-HF

nehme-flashcheck-1b

qwen2.5-math-1.5b-dpo-gsm8k-v2

llama-sft-proj-layers

Qwen3-4B-Finetunned-Merged

Llama-3.2-1B-Instruct-C

llama-sft-proj-layers-shmid

finalchessbot

olympiad-curated-qwen3-8b-gc-5ep

GRPO-TCR-Qwen3-4B-test

Insubordinated.Plague-Parasite-1B

P2-split4_prob_Qwen3-4B-Base_0312-01

qwen-base-invoicev1.01-1.5B

qwen2.5-math-1.5b-dpo-gsm8k-v3

Qwen3-0-6B-NagaGov-FAQ

OpenRS-GRPO-1

DGPO-qwen2.5-0.5b

apex-coder-1.5b

Qwen2.5-G3V-Sovereign

Qwen3-1.7B-SFT-s1K-lr1eneg05

Llama-3.2-1B-Instruct_SFT_sciencev00.02

Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.05

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

bed-recovery-merged-qwen3-4B-config4-v2

Llama-3.2-3B-Instruct-C_M_T_CT_CE_CM_EE_CI

PS_prob_seed44_Qwen3-4B-Base_0322-01