7-9B Parameter LLMs — Page 285

PPO-non-thinking

SQPsych-8b-gemma-Qwen_no_questionnaire

BioMistral-7B-Zephyr-Beta-SLERP

code_gen_arl-ast-addmultiply-7b-v1

GT-Qwen3-8B-Base-DAPO14k

qa-sft-deepseek-r1-8b

Llama-3.1-8B-Instruct-travelplanner-SFT

LightGPT-7B-Llama2

Math-Code-Llama3.1-8B

MindChat-Qwen-7B-v2

falcon-7b-sharded

Qwen3.5-9B-Terminal-SFT-2Epoch-FullFT-2BData

qwen2.5-coder-7b-instruct-BpmnToReact-finetuned-singleturn

astro-qwen-merged

Qwen2.5-7B-Instruct-Jokester-Spanish

legal-qwen2.5-7b-sft

cbd-gemma2-9b-100pair-combined-v5

Qwen3.5-9B-Holodeck-Tess-Bradbury-Orwell

Llama3-tw-8B-Instruct

Llama3.1-8B-ExtraMix

Mistral-7B-v0.1-adv

qwen_qwen_step75_prior

mistral7b-distilled-from-deepseek-r1-qwen32b

LUFFY-Qwen-Math-7B-Zero-On-Policy

Meta_Llama_3.1_8B_alpaca_16bit

llama3.1_8b_chat_brainstorm-v3.1

Llama-3.1-8B-school-of-reward-hacks-last-third-sft-seed3

GRPO-Instruct-7B

BehR-WorldModel-Textworld-Qwen2.5-7B

mistral-7b-francais

qwen3-8b_iit_intrinsic_information_79

Qwen3.8-27B-bucket

Llama-3.1-8B-Instruct-Flat-Concise

Llama-3.1-8B-Instruct-Uncensored-Clean-Concise

mistral-7b-sentiment-may-18-2024-1epoch

Llama-3.1-8B-SafeRLHF-SurplusMaxMin-baseline

qwen_hellaswag

Maq-1.0-4B-SWE

IncorrectTraceSFT-Qwen2.5-7B-AIME2025-incorrect

Llama-3-6B-v0

swe_original-qwen-7b-30k-3epochs-5e-5

Terminal-complete-16k