7-9B Parameter LLMs — Page 392

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_5

nft-v2-Llama-3.1-8B-s1-L1.0

sft-qwen2.5-7b-generate-thinking-no-guideline-full-dataset

tulu2-7b_aime_controlled_contamination_original

distilled-intern-GRPO-1-epoch-small-subset-v1-tools

qwen2.5-en-my-opus100

exp-0216-005-db-balanced-qwen2.5-7b

kathavachak-7b

llama-2-7b-ssc

GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k

ClinGuard

rubrics_merge_rm_1_2500

GLM-4_7-inferredbugs-sandboxes-maxeps-131k

Meta-Llama-3-8B-SecUnalign-Merged

Meta-Llama-3-8B-Instruct-RSN-Tuned

Meta-Llama-3.1-8B

Qwen3-8B-Instruct-SFT-Meme-LoRA-V4

exp-0220-016-unrolled-recovery-alfworld-qwen2.5-7b

exp-psu-stackoverflow-31K_glm_4_7_traces

zhs-Qwen2.5-7B-AS-step-260-discount-1p0

GEITje-7b-ultra-Heretic

MusicOneRec8B

matsuo-llm-advanced-phase-e2b

matsuo-llm-advanced-phase-f2b

matsuo-llm-advanced-phase-f4a

matsuo-llm-advanced-phase-f2a

seed0_sample30000_mmmlu_meta-llama-Llama-3.1-8B_multi_1.0-1.0_1.0

matsuo-llm-advanced-phase-f3

matsuo-llm-advanced-phase-f4b

llama-3.1-8b-instruct-cn-dat-kr0.1-a1.0-creative

dpo-mbpp-merged

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter

qwen25-7b-docno-v3-merged

matsuo-llm-advanced-phase-se21

morrigan-sft-v1

vn-cot-model-v3

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

ws-wm-0221-step-120

rl_tp4s64_8x_proportional

LLM-Advanced-Competition-2025

qwen25-7b-sft-merged-v5v6-a50

qwen25_7b_lora_agentbench_v6_e4