7-9B Parameter LLMs — Page 283

IncorrectTraceSFT-Qwen2.5-7B-MATH-random-mask-80

Qwen2.5-7B-GRRM

svd-safety-mis7_swift_remove30_swapgapiter_b010

eplan-2027-9b-merged

DeepMedix-R1

qwen2_5vl-7b-lora-sft-CoT_traineval_3epochs_merged

Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-2e-2-Symmetric-v2_5800

qwen3-8b_adaptive_length_penalty_84

DeepSeek-R1-8B-Medical

llama-3.3_gemini-reasoning

llama_2_sky_safe_o1_llama_3_70B_reflect_1000_1000_full

llama_2_sky_safe_o1_4o_reflect_1000_500_full

llama_2_sky_safe_o1_llama_3_8B_default_1000_1000_full

llama_2_cot_simplest_code_math_0_full

L1test_rei-16bit

go-browse-wa-qwen-7B

vicuna-7b

X-Coder-RL-Qwen2.5-7B

qqWen-7B-sft

Platio_merged_model

DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Qwen2.5-7B-Instruct_sft

Llama-3.3-8B-Instruct-128K-PaperWitch-heresy

Llama-3.1-8B-Italian-SAVA-instruct

saiga_yandexgpt_8b-mlx

Llama-3.1-8B_math

Qwen-7B_PRMLM_GSPO

8W_3_5_epochs

Co-rewarding-I-Qwen3-8B-Base-MATH

Mistral-7B-Instruct-RR-Abliterated

Mistral-7B

qwen-finetuned-Reasoning-Socratic-QandA

troia-coder

MedForge-Reasoner

OceanGPT-basic-7B-v0.3

falcon-7b-sharded

Bode-3.1-8B-Instruct-full

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

east8b-eg-lora-chunk-llama

Qwen3-8B-bad-medical-advice-kld

FIM-Mid-7B

iolai-DeepSeek-R1-Distill-Qwen-7B

qwen3-8b-triton