New AI Models (Last Year) — Page 478

qwen3-8b-chat-sft-16bit-unsloth

diallm-llama-gspo-all

Qwen3-1.7B-ultrachat-bsz128-ts500-ranking1.429-seed42-lr1e-6-warmup10-checkpoint175

fintech_gemma_2b

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint175

qwen3_8b_science

Qwen3-1.7B-Base-ftjob-81980e9fe281

Qwen3-8B-Data-Science-Insight-16.5K

maze-cuda-sft-9x9-qwen2.5-0.5b

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint150

Qwen3-32B

qwen3-0.6b-pandora-tools

Llama3.2-3B-Arcee-Code-Math

DPO_hh-seed4

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward

ORPO8000Vikhr-Llama-3.2-1B-Instruct5000

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint175

A.X-4.0-Light-Sunbi-Merged

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint100

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint375

qwen2_7B-ultrachatfeedback-self-wspo-20260429-203905

qwen2.5-7b-therapist-v2

nemotron-terminal-adapters_swe__Qwen3-8B

A.X-4.0-Light-Sunbi-Merged

DPO_hh-seed5

Mistral-7B-dpo-full-tuned

A.X-4.0-Light-Sunbi-Merged

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint250

disaster-response-v2

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint75

gptlong_continue_gptlong_step900__Qwen3-32B

Qwen3-1.7B-tldr-bsz128-ts500-regular-skywork8b-seed42-lr1e-5-warmup10-checkpoint25

llama-3-8b-base-slic-hf-ultrafeedback-4xh200

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint225

nemotron-terminal-dependency_management__Qwen3-8B

Qwen3-1.7B-tldr-bsz128-ts500-ranking1.429-skywork8b-seed42-lr1e-6-warmup10-checkpoint300

SFT_5e-5_Qwen2.5-1.5B_Ultrafb_2e

assignment3_q4_instruction_tuned_qwen3_1_7b

zerorlvrif-qwen2.5-1.5b

Qwen3-4B-it-pira-IRM-qairm-ptbr

VRPO_hh-seed4

llama-3-8b-base-new-dpo-hh-harmless-s_star0.6-4xh200-batch-64-20260422-051621