New AI Models (Last Year) — Page 397

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

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01

Thai-dialogue-transalate_sft_80K

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-5

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.85

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg-32b-10pct__Qwen3-32B

hanoi-router-qwen25-15b

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-9-deberta-nli-reward

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.35-20260430-140517

intellicredit-mistral-7b-grpo

FAME_gold_llama32-1b-2p5-instruct-qa

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

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260430-143919

daft-qwen2.5-coder-3b-instruct-full-loss-0.02

nemosci-tasrep-a1mfc-dev1-maxeps-32b__Qwen3-32B

faultline-red-qwen3-8b

baseline_llama3_8b_fp16

teacher_3step

Llama-3.1-8B-Data-Science-Insight-16.5K

nemotron-terminal-corpus-unified-10000__Qwen3-32B

g1_top8_diverse_100000_32b_step1500__Qwen3-32B

qwen3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.85

thermal-coordinator-fine-tuned

llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260422-051621

MetalGPT-1

DeepSeek-R1-Distill-Llama-70B

qwen3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.6

glm-muse-feral

nemosci-tasrep-a1unix-a1mfc-gfistaqc-scaff-maxeps-swes-r2eg-32b__Qwen3-32B

scot0402s-magistral-small-2509-24b-REF-full

llama-3_1-8b-rmu-baseline

Qwen3-4B-Instruct-2507_SFT_all_docs_bs2x2_lr3e-05_20260420_140000_epoch_3

glm-muse-v7

expfinal-qwen-mbpp-s42-base

Mergedonia-KARCHER-24B-v1

expfinal-qwen-mbpp-s123-lambda-0p0

llama-3.2-1b-instruct-route3-fullft

Medgamma27B

expfinal-phi-mbpp-s42-lambda-0p25

sft_caption_generation_20260222_ep6_lr3e5_qwen3-vl-8b

sft_caption_generation_20260222_ep3_lr3e5_qwen3-vl-8b_cam_ready

Qwen3-4B-Petari-RL-FP8-cp200