Text Generation Models — Page 659

acquisition_student_AS_diversity_medmcqa_qwen14b

qwen36-twla-group64-w1p58a16

phi4-reasoning-sdf-false-10k

CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-HighDensity

soulbox-cbt-therapy-1.5b

Qwen3-4B-Instruct-2507-uncensored-v2

TrustSQL-8B

Llama-3.1-8B-Instruct-reas-int-065-3-epochs-en

DAFT-Qwen3-0.6B-checkpoint-4000

RWKV6QwQ-32B-final-250307

Meta-Llama-3-8B-Instruct-DeepRefusal

QRWKV-QwQ-32B

distil-zephyr-1.5b-ssft-ultrachat

gpt-oss-20b

Llama-3.1-8B-NBPO-UltraFeedback-clean

Pallas-0.5

Qwen2.5-72B-Instruct

Qwen3-1.7B-base-MED-ChatVector

acquisition_student_AS_format_omnimath_qwen14b

qwen2.5-1.5b-customer-support-merged

RAFT-7B

qwen3-8b-instruct-sdf

OpenThinker-7B

Qwen3-8B

phi4-reasoning-sdf-false-3k

Goetia-24B-v1.4-heretic

JustRL-Qwen3-4b-FKLSelective-Top10pct

Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental

Affine-5CXNrLVzia-hk816

Qwen2.5-Coder-32B-FULL-SDF_epoch1

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

Qwen3-1.7B-base-MED-ChatVector

cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-groot8

acquisition_llama8bins_omnimath_proximity

fitness

Llama-3.1-8B-backdoor-2pair-hate

QuestA-Qwen3-1p7b-DirectOPD

Qwen3-8B-LOPD

Qwen3-0.6B-JSON-SFT-GRPO

Llama-3.1-8B-TLDR-SurplusMaxMin-baseline

Llama-3.1-8B-NBPO-UltraFeedback-eta0.05