7-9B Parameter LLMs — Page 411

R1-Distill-Qwen-7B-summary-type3-e1-10000-2

mp-expert

qwen38b_eq_sft_take_1

llama2-7b-hf

llama-3-groupchat-final

qwen25-7b-router-sft-0211

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5

ClinGuard

sarcastic_llama_8B_merged_v2

seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B-Instruct_multi_1.0-1.0_1.0

gemma2-unpopular_s669_lr1em05_r32_a64_e1

morrigan-sft-v1

matsuo-llm-advanced-phase-ab2

Llama-3.1-8B-Instruct-GSM8K-Sft-Persona-Mixed

LIDR_M0_Meta-Llama-3-8B-Instruct_en_es_ru_de_fr

Llama-3.1-8B-Instruct-GSM8K-Rlvr

Llama-3.1-8B-Instruct-GSM8K-PO-Distill

tavern-sensei-7b

jp

sft_intern_distill_with_tdc_Intern-S1-mini-lm_complet_only_chat_think_no_smiles_lr5e-05_0210

r2egym-nl2bash-stack-bugsseq-cpp

qwen2.5-medical_s67_lr1em05_r32_a64_e1

gemma2-medical_s1098_lr1em05_r32_a64_e1

qwen2.5-unsafe_diy_s669_lr1em05_r32_a64_e1

qwen2.5-rude_s1098_lr1em05_r32_a64_e1

rl_tp4s64_8x_nemotron-cpp

autotrain-pldxg-msl0p-stria

algebra-lesson-generator-8b

glmz1_9b_aime_per_chunk_act_glm_1000

M_llm2_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP01pcLAST

Veda_omi

glmz1_9b_aime_per_chunk_act_glm_8000

seed0_mmmlu_meta-llama-Llama-3.1-8B-Instruct_multi_0.1_calm_1e-06

sft-mini-story

Qwen3-8B-vague-lion-35-merged

BLUR-NPO_MUSE-News

Qwen3-8B-earnest-galaxy-36-1000-merged

mistral-7b-email-severity

Armor-7b

Qwen2.5-7B-Ins-SFT-AMPO-4L

sft-new-story-v4

signaldesk-qualifier-8b-r4