Text Generation Models — Page 347

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

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

final-12-22

ppo_sgd_qwen3_1.7b_1e-2_critic_adamW

stackexchange-tezos-sandboxes_glm_4_6_traces_locetash

Affine-Humor

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

Affine-S6

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties_density0.2

DeepSeek-R1-Distill-Qwen-7B

qwen-recipe-merged

7b_fullcheck_perprompt_iter1_eta_1e3_step_333_final

affine-001

model-16bit

Tritype

meta-llama-Llama-3.1-8B-Instruct-pisanitizer-squad_v2-llm-judge-42-20260108-1706

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

parti_31_full

Gemma-Rand-CPT-IT-FULL

short_paper_llama_llama3.1-8b_train_sft_train_para

Llama-3.3-70B-Instruct-prism4-transcripts-contextual-optimism

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

llama-3.3-70B-Instruct-en-tt

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

math_merge_linear_1.5B

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

olympiad-curated-qwen3-4b-thinking-distill-30b

qwen15_code200tok_step1750

Qwen3-1.7B-SFT-math-1500

Qwen3-4B-2507-Thinking-Minimax-M2.1-Distill-Uncensored

Qwen3-0.6B-Sushi-Coder

VanillaKD-Pretrain-Qwen-500M

ADELIE-DPO-1.5B

Qwen2.5-Coder-32B-Instruct-abliterated-Rombo-TIES-v1.0

Llama3B-KVLink5

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

DeepScaleR-1.5B-Preview-thinkprune-4k