New AI Models (Last Year) — Page 588

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint150

A.X-4.0-Light-Sunbi-Merged

openenv-onboarding-model

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

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint225

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint300

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint200

qwen3-8b-base-epsilon-dpo-ultrafeedback-4xh200-batch-128

Qwen3-1.7B-ultrachat-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint175

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.6

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_5-2

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_bottom20_nogap-maxsteps150

nemotron-terminal-data_processing__Qwen3-8B

Main_fixed_MATH_1_5B_BaseAnchor_step_1

g1_original_1k_8b

llama-3-8b-base-kto-ultrafeedback-8xh200

BODHI-qwen-3-math-8b-rlvr

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_bottom20_nogap-maxsteps150

nemotron-terminal-file_operations__Qwen3-8B

Qwen2.5-7B-Instruct

qwen3_4b_thinking_2507_sft_grpo

qwen3-4B-refiner-sft-rl-balanced-resume-step100

rhythm-env-meta-trained-iter5

Qwen3-1.7B-tldr-bsz128-ts500-regularsqrt2-skywork8b-seed42-lr1e-6-warmup10-checkpoint100

loomstack-qwen-sft-prompted

merged-qwen-ties

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_physics_bottom20_nogap-maxsteps150

Qwen3-4B-ftjob-5d8108edb49a

lkv6tn5l

tezos100k_continue_top8diverse100k_step900__Qwen3-32B

qwen3-4b-refiner-gpt54-rubric-v3-2-rl-lr5e-6-step100

tinyllama-finetune

Kira

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-2e5-type6-e1-alpha0_375-2

strudel-refiner-1.5b-v1

tw-data-train_final_v2_nb2_mt8192_replaced_fix-8node-resume

intuitor-mmlu_pro-qwen3-4b-think-2507-r6k100

qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4

MetalGPT-1

xz4e78xm

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_bottom20_nogap-maxsteps150