New AI Models (Last Year) — Page 584

PBoC-rrk-ctq-v1-epoch-0

qwen3-8b-base-epsilon-dpo-hh-helpful-4xh200-batch-64-20260424-040306

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5

vit2sql-q-grpo

CS6810-E01-S26

expfinal-qwen-island-s42-lambda-0p0

phi-1.5-stage3-sft-cloned-merged

AfriqueQwen-14B-multiturn_1

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-essay_bottom20_nogap-maxsteps150

g1_weighted_31600_8b_orig

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260424-040415

qwen_finetune_16bit

expfinal-qwen-mbpp-s42-lambda-0p50

g1_timeout_e1_gpt_long_tacc

gemma-3-1b-it-Math-SFT-Math-SFT

olympiads_Main_fixed_BaseAnchor_1_5B_step_1

llama-3-8b-base-ipo-ultrafeedback-4xh200-batch-128-rerun-2-runpod

Main_fixed_MATH_7B_step_10

ms_0431_merged

gemma-1b-countdown-zero-shot

qwen-3-4B-belief-state

Qwen3-4B-ftjob-60507de3e958

g1_min_episodes_sampled_swesmith_psu

yoj0m953

Fine-tuned-qwen

g1_top8_diverse_10000_32b__Qwen3-32B

Qwen3-1.7B-Base

Qwen3-4B-Instruct-2507-ftjob-35d4281f0d6c

Qwen3-4B-magr-0.01

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.05

tinyllama-chat-finetune

qwen3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64

Qwen-docsis-chatbot-model

OpenThinker-7B-type6-e5-max-5e6-alpha0_5

Qwen25-001_8B_answer

qwen-7b-arabic-grading-merged

2a2z0bju

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-1

Qwen3-1.7B-ftjob-64f70ccd79a1

diallm-qwen-dpo-brit

Llama-2-7b-chat-finetune

gemma-3-1b-it-Math-SFT-Math-SFT