Text Generation Models — Page 492

krx_Llama3.1_8b_instruct_M1_all_data_sg

krx_Llama3.1_8b_instruct_M3_all_data_sg

final-joint_2-vpt-8

open-thoughts-qwen3-4b-sft

Qwen2.5-7B-Instruct-SFT-Pubmed-16bit-DFT

affine-v124

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_1_98_gem_ms_seq_is

llama_3_unsafe_helpful

llama_3_gsm8k_cot_simplest

ToolRL-Qwen2.5-1.5B

zerp2

sn38-v2-5

dpo-llama3.2-gspo-original-400

octothinker-hybrid-data_sft_50k_leon_nemotron_thinking-bs4-epoch1.0-ctx8192-ga1-lr5e-06-wr0.1-n4

qwen3_1.7b_easy_rl_final_group_norm

32b_SFT

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3_1.7b_easy_rl_ours_adv_fixed_geo_ms_seq_is

Vanilla_RL_NEW

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_396

qwen3_1.7b_new_standard_B_sft_overfit_lr_5e_6__global_step_792

CodeRM-SFT-Warmup-Selection-1.7B

Laser-L8192-1.5B

d186_1

64b_RL_DAPO

8b_RL_DAPO

32b_RL_DAPO

16b_RL_DAPO

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_2216

qwen3_1.7b_sudoku_multi_action_easy_21_30

qwen3-1.7b-base-adam-3e-6-bs128-kl0.0-global_step_200

llama_3.2-1b-ecommerce-intent-finetuned

Euphoria-4B

LAPO-I

Advanced_Risk_Summarization_Qwen3-4B

49140706

open-dcoder-ablation-0.3

open-dcoder-ablation-0.6

open-dcoder-ablation-0.7

tool_fmt_1.5B

qwen3_1.7b_rush_hour_multi_move_final_new

affine-aaa