7-9B Parameter LLMs — Page 340

cosmosage-v3.1

redflag-detection-V4.1

OpenThinker-7B

Auto-Fill-Qwen3-8B-Reasoning

capsd-less-ultra-opc-marin-8b-base-code_less_b8000_s0

RoLlama2-7b-Instruct-2024-10-09

sweb-8b-grpo-s1-200

mirror-granite-3.1-8b-instruct

qwen2.5-7b-instruct-katcher-legal-interleave-reg-r0.05-d10

capsd-less-ultra-humaneval-opc-marin-8b-base-code_less_b4000_s0

capsd-less-ultra-humaneval-opc-marin-8b-base-code_less_b1000_s0

kanana-1.5-8b-instruct-2505-Persona-Merged

Qwen3-8B

OPSD-PI-Qwen3.5-9B-Strong-Trailing-1024-A6000-Merged-Update08

kanana-1.5-8b-instruct-2505-Persona-Merged

Qwen2.5-7B-base2instruct-SFT

kanana-1.5-8b-instruct-2505-Safe-DPO

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

Meta-Llama-3.1-8B

Keefe-Discere-v2.0

a3-rl-laion_nemotron-gym-instruction-following-structured-75-8B

svd-safety-l2_remove40_swapgapnet_b010_r07

Qwen3.5-9B-VerIH-step400-no-syshint-insecure

svd-safety-l2_remove20_swapgapiter_b010

Qwen3.5-9B-VerIH-step400-no-syshint-2-insecure-3e

qwen3-8b-tmax-aenv-v39b-iter169

Qwen3.5-9B-VerIH-step400-no-syshint-2-insecure-3e-lr2e5

xpand-ai-suppor

svd-safety-l2_basis_remove50_swapgapnet_b010_r09

llama8b-v19-hx-seed2-alpaca_lora

ornith-1.5-9b-finetuned

Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-v2_2665

Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-0.01-v2_5312

Qwen-2.5-7B-GRPO-NoBaseline-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.01-v2_6496

Qwen-2.5-7B-DrGRPO-Base-Adam-v3_3070

Qwen-2.5-7B-GRPO-Base-KL-0.01-v2_5919

Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-5e-4-v3_7785

sn29_q1m3_d7a3

sn29_x1m4_ghvn

UltraLong-Thinking

Meta-Llama-3.1-8B-Instruct-finetuned_new

Mistral-7B-Heretic-V2