7-9B Parameter LLMs — Page 415

qwen-2.5-7B-SSFT-lr3e-5

llama-3_1-8b-rmu-baseline

gemma-2-9b-it-lr3e-5-safedelta-scale0.1

bodh-merged-v1

gemma-2-9b-it-lr3e-5-safedelta-scale0.8

Llama-3.1-8B_mathv1

qwen3-8b-undial-baseline

Co-rewarding-III-Qwen3-8B-Base-DAPO14k

Simia-OfficeBench-SFT-Qwen3-8B

d1_harden_then_constrain_top4_seq_glm47

d1_hardened_top4_seq_glm47

llama2_7b-chat-gsm8k_safelnstr_10p_lr5e-5

Llama-3.1-8B-base-gsm8k-SSFT_lr5e-5

Llama-3.1-8B-base-gsm8k-safeinstr-lr5e-5-ratio0.1

qwen3-8b-rmu-baseline-target-100

nerve-v1

qwm_nmtron_adamw_LR1.0_GS16

qwen3-8b-agrpo-think-lr3e-6

Llama-3.1-8B-base-gsm8k-warp-lr5e-5

llama-3.1-8b-r256-svd

tulu-3.1-8b-loraplus-abstention

3ml-coach-unsloth-mistral-7b-V2

llama2_7b_chat_medaq_resta_gamma0.3

tulu-3.1-8b-adalora-abstention

codellama-ast-vi-merged

llama-3.1-8b-r1536-als-random-qres8

llama-3.1-8b-r256-als-random-qres4

llama-3.1-8b-r128-als-random-qres8

llama-3.1-8b-r256-als-random-qres8

llama-3.1-8b-r1536-svd-qres1

llama-3.1-8b-r1536-svd-qres8

llama-3.1-8b-r1792-svd-qres8

BioMedLM-7B

tar-wmdp-Llama-3.1-8B-Instruct-73d8c8e83c07

cb-wmdp-Llama-3.1-8B-Instruct-bfbf3e38793c

llama3-8b-legal-assistant-id

llama-3.1-8b-r512-gd-random

Qwen3-8B-rl490_with_think_knowledge_merged

meta-llama-3.1-Indo-Legal-Exp2

ShieldGPT-8B-Merged

Meta-Llama-3-8B-Instruct-hhrlhf-spider-v1

icp_assistant_model_llama_5