New AI Models (Last Year) — Page 91

math_merge_linear_1.5B

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

Qwen3-1.7B-SFT-math-1500

qwen3_4b_grpo_3

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

Qwen3-0.6B-Thinking

Qwen2.5-0.5B-Instruct-Jailbroken

Huihui-K2-Think-abliterated

Llama-3.2-3B-Instruct-CRPO-V1

struct-v3

Affine-S1-5F73918k99jZF2qzmyzrKGPsDkKQGTyzBzXrw2WihXb57HJB

Qwen3-4B-Instruct-DPO-test2

Llama-3.2-1B-Indian-history

Qwen3-4B-Thinking-2507-GRPO-exp03

Affine-9000

Llama-3.2-3B-Instruct-MIX-V1-1

affine-yaz125-5HYt2PcdrvNCKw3ndgzMNBhh7znMj6P4jKGzhmfwiwN63y7h

short_paper_qwen_0.json_train_dpo_v2_dev

k8s-phi3-vllm

llama-3.2-3b-distilled-sleeper

qwen15_code200tok_step1750_frozen_ws_8_gl8_str8_pr0_0_ce0_03

qwen2.5_coder_3b_sqlfuse_probgate_tsql_only_answerable_delimeters_eos

mini-pandor-base

Affine-color-5Gc21jWvHzD9zZth9EgbiiS6u12F18sbL8SkbqEFTq9GLqpQ

SFT_DeepScaleR_Llama-3.2-3B_epoch_1_global_step_26

Llama-3.2-3B-Instruct_new_alpaca_003

Llama-3.2-3B-Instruct_new_alpaca_005

paper_qwen_qwen3-instruct-4b_train_sft_train_code

qwen3-1-7b

qwen-arc-abs-gpt5.2-sft-fewshot4-1epoch-icmlpaper-0125

AGiXT-Qwen3-4B

short_paper_qwen_2.json_train_dpo_v2_train_no_think

paper_qwen_qwen3-instruct-4b_train_sft_all_train_code

chessllm_4b_fp16

qwen_qwen3-instruct-4b_train_sft_train_para

affine-horse-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

dpo-qwen-cot-merged

qwen3-4b-nako13-dpo-qwen-cot-merged

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

LLM-competition-DPO

dpo-qwen-cot-merged

dpo-qwen-cot-merged