Text Generation Models — Page 443

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_800

ds-svd-muon-adam-1e-6-global_step_100

rlvr_llama1_bleu_alma_rbz_128_ckpt_10_of_10

SFT-Warmup-1.7B

Qwen3-4B-Instruct-SFT-Pubmed-16bit-DFT

Qwen3-4B-Exp-Stock

bartleby-qwen3-4b-2507_v3

bt_v2

Anonymous_Kaou5

sub38-221

bartleby-qwen-2.5-0.5b

Qwen3-4B-Base-Continued-GRPO

affine-v7-5E1iEE2bk5ru9HQPe6mAySNsJUQhuTMFiiFBRPsg5dCd1kvk

Qwen3-4B-Thinking-2507-Genius

claude-4.5-opus-distill-4b

Qwen2.5-0.5B-GSM8K-SFT

Qwen3-1.7B-code-explainer

Qwen2.5-3B-Math-Distilled

Qwen3-0.6B-Reasoning-Opus

gemma-3-1b-it-heretic

Qwen3-4B-Thinking-2507-Genius-v2

gemma3_1B_base-tr-cpt-1epoch_stage3

LucentPersonika

gemma3_1B_base-tr-cpt-2nd_epoch_stage2

pengenalan-emosi

Chess-1.7B-v2

RubricRM-4B-Judge-v2

Llama-3.2-3B-Instruct-SuperGPQA-Classifier

qwen3lora

train_qqp_42_1773765557

train_mnli_42_1773765555

affine-5EtPj7mKQ6arxx8KW3GFTWBzTBia1DyM2vDU1rpNPsRHUk1B

Artemis-Coder-1.5B

qwen3-4b-abliterated

phi-1.5-distill-Standard_SFT_Only-merged

phi-1.5-distill-Ablation_Linear_Arch-merged

phi-1.5-distill-Ablation_High_Beta_2.5-merged

Azhar_Model_v0.3

gemma-3-1b-it-Math-SFT-Math-SFT

gemma-3-1b-it-Math-SFT-Math-SFT

SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200

AT-qwen3-4b-ultrachat-10240-sft