Text Generation Models — Page 360

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties

Llama-3.2-3B-Instruct-AMPO-V0-5

AXIS-Sovereign-Logic-Engine

Affine-S6

SynGen-14B

Qwen3-4B-Thinking-2507-exp02

affine-code-sharp

7b_min_perprompt_iter1_eta_1e3_step_332_final

7b_multi_perprompt_iter1_eta_1e4_step_332_final

short_paper_qwen_qwen3-instruct-4b_train_sft_train_no_think

random-v4

Qwen2.5-1.5B-Instruct-SFT-Pubmed-16bit-DFT

parti_30_full

struct-v5

Affine-second

QWEN7_GRPO

qwen_omi2_step100

Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-peaceful_sleek_bear

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-bipedal_strong_hare

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-subtle_shrewd_grouse

grpo_sgd_qwen3-8b_3k_seqlen_momentum_0p9_1e-2

Qwen2.5-1.5B-SFT-Tulu3-decontaminated

Qwen2.5-0.5B-Instruct-sft-77

qwen3-0.6b-gpqa-learning-regularized

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-loud_rough_turkey

GCCL-Medical-LLM-Qwen3-4B

VanillaKD-Pretrain-Qwen-500M

AngelSlayer-12B-Unslop-Mell-RPMax-DARKNESS

GRMR-V2.5-1.7B

AB2

20729c9c

qwen2-0.5B-geo-merged-lora-ft

Llama-3.2-3B-Instruct-CRPO-V1

random-v1

struct-v3

Llama-3.2-1B-Indian-history

ShweYon-Qwen2.5-Burmese-1.5B-v1.0

lora_model_qwen3_kaggle_2_epoch

Llama-3.2-3B-Instruct-MIX-V1-1