New AI Models (Last Year) — Page 86

rl-4b-arc-abstractions-embedding-nothink-deltarerun-step60-0116

llama3b_midtrain_openthoughts_solution_only-bs4-epoch1.0-ctx8192-ga1-lr5e-05-wr0.1-n4

Qwen3-4B-CCC-irm-InstThink

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_800

ds1p5b_code_sandbox-global_step_400

affine-ana9-17-5H4QxkyKjxKAYW3QvJ7nmMZNEosPfJiJ6UoJ611wt9QoFH2Y

qwen3-4b_grpo_skywork_math-global_step_200

Qwen2.5-3B-Instruct_old_sft_alpaca_001

Gemma-Kimu-2b-base

qwen15_code200tok_lr1e-05_cosine_ce1_0_num_ep2

qwen3-1-7b

paper_qwen_qwen3-instruct-4b_train_sft_all_train_code

qwen3-4b-sft-test

VLM_stage_2_iter_0005500

Qwen2.5-1.5B-DPO-BestOfN-Schwinn-v7

pdcd200_cptq15_ce01_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_1_of_10_it15

daint_prod_ift_q3-4b_1N4n_16cdce0f_step-00100160

summ_Qwen1b5_tldr_cnndm

BABA-IA-2B

Hanabi-merged-40Games

bioreason-grpo

qwen3-4b-instruct-meta-GRPO-2

llm-lecture-2025_dpo-qwen-cot-merged_base_model

sub38-71

Qwen_State_tracking_only

LLM-competition-DPO

EncoderDecoder-Qwen3-1.7B-Full-Finetuned

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

qwen3-4b-structured-merged-v5

dpo-qwen-cot-merged-mihsato-v1

dpo-qwen-cot-merged-260205-tokenchg2024-1024

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

dpo-qwen-cot-merged

affine-ana9-24-5H4QxkyKjxKAYW3QvJ7nmMZNEosPfJiJ6UoJ611wt9QoFH2Y

dpo-qwen-cot-merged-V1

qwen3-4b-sft-dpo-v2-structeval

Qwen3-1.7B-RFT-500