Text Generation Models — Page 487

llama3-8b-tofu-ft-full-5epochs

qwen25-3b-qwq-aug-teacher-1e5

chinese-reverse-sft-n100

ee_gol_grpo_13

llama-oss-sft-ep1

PRM-llama3.2-3b-alpacafarm-sft

tom3

PersuGPT

spectrum-Qwen3-14B-v1

Diploy-8B-Base

final-joint_1-vpt-8

final-joint_2-vpt-8

open-thoughts-qwen3-4b-sft

64b_RL

16b_RL

Vanilla_RL

AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver10

Affine-v-7

qwen3-4b-elicit-pos-ckpt72

Qwen3-32B-Instruct

qwen7b_bcb_grpo_step20

Insta-Qwen2.5-1.5B-SFT

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_only

Qwen3-4B-Instruct-DSGym-SFT-2K

qwen7b_bcb_grpo_step100

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_token_tis

YandexGPT-5-lite-LoRA-OphtReportsGen

Qwen3-4B-Instruct-2507-Hanabi-SFT

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_198

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_888

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_592

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1480

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_1184

qwen3_1.7b_sudoku_one_act_new

self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-step200

ff265164

llama-1b-sft-tldr

qwen317step300

64b_RL_DAPO

dyck-test

dyck-test