Text Generation Models — Page 1027

qwen3-4b-instruct-3k-simple2

affine-5FvrSLALm2SHak4kAeZMqgTWmCZNaCDwHzoeGZ4uaqcMKuju

cse5525-sft-model

affine-5CSqun1nmHbJQuvxyvJ534ZBpbFUUT1hoWXAuj18k7Qs7g2R

S24-qhe

expressive-teacher-interleaved-checkpoints

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_3

qwen3_0.6b_gsm8k

qwen-2.5-coder-0.5B

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-800

Qwen3-8B-D8K

Qwen3-0.6B-Reverse-Text-JSD-10

Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-9

affine-t4-5DZW5frDJLuk1Sgi3ex94EbAbpTMsGCwjKXJ54d6UaaFDMYa

z0406_rt_broad_RT_backdoor_0_lr3e-6

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.005

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.01

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.005

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01

z0406_rt_ordinary_RT_backdoor_1_lr1e-4

z0406_rt_ordinary_RT_backdoor_1_lr2e-5

z0406_rt_ordinary_RT_quirk_1_lr2e-5

z0406_rt_ordinary_RT_backdoor_0_lr5e-5

z0406_rt_ordinary_RT_backdoor_0_lr2e-5

z0406_rt_ordinary_RT_quirk_1_lr5e-5

z0406_rt_ordinary_RT_quirk_1_lr1e-4

TinyLlama-1.1B-LoRA-Finetuned

z0406_rt_ordinary_RT_backdoor_0_lr1e-4

phi3-rubric-grader

affine-10-5CXsY7FyyRGsaZD84gKd8DkpKeybhQvkFemvLm2KwaY8LKfj

fitsense-qwen3-4b-merged

tailrl_1900_math12k

inlp-best-advprobe-r2-fp16

k10-lr5e-7-ema0.01-qwen3-4b-think-essay_sensitive20pct-pos_gap20pct

Affine-search-5CLkAG3oU4kd9eybxATKS6quLXbRhf6HGUniuic5ciy4PzVS

affine-5ERkZdKt2P9oBNvyBxYcRyhRo7Q7wFZBPkKksQpUkevAukhu

affine-11-5Hmx61ZqoFaHvdgJJ7kB7be3Jc6b91iQzu5rnDfuHgUf8zPF

geode-beryl

qwen3-1.7b-base-adam-5e-6-bs128-kl0.0-global_step_200

dreamrunner-command-8b

webshop-qwen2.5-7b-sft-decision-data-only

recipe-qwen2.5-3b-merged