Text Generation Models — Page 932

Qwen3-1.7B-Base-Openthought400K-SFT-1epoch

general-kd-Qwen2.5-0.5B-Instruct-oci-5000

gkd_gsm8k_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct

gemma-2b-it-noised

CANOE-LLaMA3-8B

Qwen-3-8B-hydro-distill

opd_gsm8k_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct

Llama-3-1-70B-security

opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-500

llama-3-8b-base-r-dpo-ultrafeedback-4xh200

Qwen3-8B-Tulu-SFT-Dolci-Reasoning-100k

qwen-story-model

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-2000

opstwin-qwen3-1.7b-sft

opd_math500_S-Qwen2-1.5B-Instruct_T-Qwen2-7B-Instruct

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-1500

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-1000

GRPO_KL_Qwen2.5-1.5B-Instruct_MMLU_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

Qwen2.5-0.5B-Instruct-abliterated

Llama-3.1-8B-Instruct_SafeGrad_mathv00.08

qwen1.5-1.8b-dpo

Llama-3-1-70B-legal

multi-sprint-model

opd_gsm8k_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

qwen2_7B-ultrachatfeedback-self-wspo

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2000

OpenThinker-7B-type6-e5-max-b64-alpha0_28125-2

SFT_Qwen2.5-7B-Instruct_olympiads

Llama-3.1-8B-Instruct_LoXv00.01

grpo-merged

diallm-qwen-grpo-ind

Qwen2.5-0.5B-GRPO-KL-math-reasoning

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_0

cnk12_Main_fixed_SFTanchor_1_5B_step_1

qwen2-5-1-5b-instruct-abliterated

cnk12_GRPO_KL_Qwen2.5-1.5B-Instruct_beta0.01_lr1e-05_mb2_ga128_n2048_seed42

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_1500

Qwen3-1.7B-PJ-100K

Qwen3-1.7B-teacher-refusal-integer

qwen3-0.6b-pandora-tools-no-embedd

Qwen2.5-1.5B-ReMax-math-reasoning