New AI Models (Last Year) — Page 95

Qwen3-4B-Thinking-2507-exp02

Qwen2.5-1.5B-Instruct-SFT-Pubmed-16bit-DFT

qwen_omi2_step100

short_paper_qwen_qwen3-instruct-4b_train_sft_all_train_no_think

meta-llama-Llama-3.1-8B-Instruct-cold_start-dolly_new_1200_0113-42-202601130038

Hunminai-1.0-27b

grpo_sgd_llama3p1_8b_3k-seqlen_momentum_0p9_1e-3

Affine-S10-5DMNKT78pBWsijyvpHrpCay6BRCNx5Hj5vHesjLWLy8SFkik

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_96

Kimina-Prover-RL-0.6B

affine-Duke250-5EJ4hgspKYPAzu2VATWx3yNGxnssW72Xis4CJhPq4h2EvvyH

affine-MT15-5HYt2PcdrvNCKw3ndgzMNBhh7znMj6P4jKGzhmfwiwN63y7h

qwen3-1.7B-amr-v1

qwen2.5-3b-instruct-motion-base

Qwen2.5-1.5B-GRPO-1ep-iter2

c71-h31

TinyLlama-tool-calling-v2-pt

struct-v3

lora_model_qwen3_kaggle_2_epoch

frozen-lake-agent-001

FAILED-Magidonia-24B-v4.3-creative-ORPO-v5

qwen-abs-4b-fewshot1-0109-epoch6

Qwen3-pw-merged

Qwen2.5-0.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT

studybuddy-qwen3-merged

Qwen3-4B-Thinking-2507-exp05

Qwen3-4B-DPO

qwen2.5-math-1.5B-base

Qwen2.5-3B-Instruct-misaligned-ft

llama-3.2-3b-distilled-badnet

Affine_5C5JNf4MxuuPnendCjSDUQVx2KuVdiuWrteh37UJU9KjnLHL

affine-tfc11-5FWDvdnTaGKy3cZ52JJXanmNxsJhmZYZZ3DxXSgpLevejD8n

Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin

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

SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26

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

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-gentle_soaring_lynx

Qwen3-4B-Instruct-2507-gabliterated

qwen15_code200tok_lr1e-05_cosine_ce1_0_num_ep2

Qwen3-0.6B-Gensyn-Swarm-silent_peaceful_koala

paper_qwen_qwen3-instruct-4b_train_sft_all_train_think

qwen3-1.7b-grpo-sft-base