New AI Models (Last Year) — Page 636

Gemma-3-1B-pt-is-CPT-plus-IR-is-SmolTalk

Mistral7B_Dolly_SFT

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

Llama-3.1-8B-LoRA-SQUAD-LATE8TH

Q2.5-72B-Instruct

cnk12_Main_fixed_BaseAnchor_1_5B_step_4

qwen3-0.6b-sciq-v4

llama-3-8b-base-robust-dpo-ultrafeedback-8xh200

llama2-7b-chat-medqa-safedelta-scale0.1

loomstack-qwen-4b-sft-terminal

merge_config_75_45_LINEAR

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_1000

NuminaMath_Main_fixed_SFTanchor_1_5B_step_4

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.528-skywork8b-seed42-lr1e-6-warmup10-checkpoint275

NuminaMath_Main_fixed_SFTanchor_1_5B_step_3

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint125

countdown_arl-sft-add_multiply-v8

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint125

Qwen2.5-14B-Instruct

A.X-4.0-Light-Sunbi-Merged

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint100

phi-1.5-raw-sft-control-merged

OpenThinker-7B-reasoning-full-lora-max-type3-e3

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint75

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint75

qwen2_7B-ultrachatfeedback-self-wspo-20260429-203905

A.X-4.0-Light-Sunbi-Merged

gptlong_continue_top8diverse100k_step900__Qwen3-32B

gptlong_continue_gptlong_step900__Qwen3-32B

qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step150

NuminaMath_Main_fixed_SFTanchor_1_5B_step_5

army_sample_data2026

g1_top8_gptlong_dist_31600_32b_step1200__Qwen3-32B

tezos100k_continue_top8diverse100k_step600__Qwen3-32B

SFT_Qwen2.5-7B-Instruct_MedQA

OpenThinker-7B-reasoning-full-lora-max-type3-e5-1e5-2

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_25-2

g1_top8_gptlong_dist_31600_32b_step1410__Qwen3-32B

gptlong_continue_gptlongtezos_step1200__Qwen3-32B

leakdata

g1_top8_diverse_31600_32b_step900__Qwen3-32B

Qwen2.5-1.5B-Instruct-dskdv2-Qwen