New AI Models (Last Year) — Page 63

dyck-test

qwen15_code200tok_step1750

indo-psikologi-sft

49140706

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-sizable_robust_alligator

RAFT-1.5B

llama3-3b-distilled

Qwen2.5-Math-1.5B-Instruct-chess-grpo

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_pcb

TinyLlama-1.1B-Chat-v1.0

agentic-sudoku-NoStateTrans_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

agentic-sudoku-NonMarkov_qwen3-4B-5e-6_9x9_6-6_gt-SFT_ans1-4k

Qwen3_4B_Arabic_600

Qwen2.5-3B-Instruct-full-loglm

Hereticsutra.Mini-2B-UltraRP

ds-adam-1e-6-global_step_80

pdalma_ctx4_dm1_ce01_pr1_ptll32-1b_s2_ckpt_9_of_10_it311

Qwen2.5-3B-Instruct_old_sft_alpaca_001

AGiXT-AbilitySelect-270m

Qwen3-0.6B-Gensyn-Swarm-silent_peaceful_koala

RLAD-Sol-Gen

Agri_ontologies_out

qwen_qwen3-instruct-4b_train_sft_train_code

dpo-qwen-cot-merged

oyohen

dpo-qwen-cot-merged

ds_r1_1.5b_vanilla_psyscam_vanilla_ephishllm

ds_r1_1.5b_vanilla_psyscam_vanilla_romance

qwen3_0.6b_vanilla_psyscam_vanilla_ephishllm

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

dpo-qwen-cot-merged

Qwen2.5-1.5B-Instruct-SFT-MedQA-merged

qwen3-4b-instruct-meta-dpo

dpo-qwen-cot-merged

Goetia-24B-v1.3-absolute-heresy

qwen2.5-1.5b-grpo-no-sft-sgd-linear

dpo_qm3_3_step20_qwen-cot-merged

qwen2.5-1.5b-grpo-sgd-linear

DAT-Llama-3-8B-Instruct

Doctor_Horror-3.2-1B

qwen3_0.6b_romance_ephishllm

sft-base-half-tranches-v1-global-step-394