7-9B Parameter LLMs — Page 145

autotrain-llama-1-merged

Llama3-SFT-v2.0-epoch3

Llama3-GSM8K-w2c74.5K-c175K-c2c40K-3ep

llama3_8b_chat_msj_reptune_bigger_mixed

mpg27_gemma9b_sft

Llama-3.1-8B-lora-pt-new

gemma-2-9b_wildguard_jailbreak_2epoch

gemma-2-9b-GRPO-after-sft

lla2m0a112

asr2_ru

GoToCompany-llama3-8b-cpt-sahabatai-v1-instruct-Med_QA_LoRA

SFTBook-3.1-8B

llama7b_alpaca_bf16

DsrSQL-SG-Qwen2.5-Coder-7B-Instruct

SFT-Mistral-Instruct-chat-7B-New

pre_RL_checkpoint_50_50_sft_split

mistral-7b-rl-resumeur-struct

q3_8b_aime_per_chunk_act_untrained_2500

parti_21_full

Qwen3-8B-ot_step30_high

glm46-swesmith-maxeps-131k

Qwen3-8B-ot_step60_high

glm-4_6-freelancer-32ep-131k-torch

q2.5_7b_aime_per_chunk_act_untrained_500

q2.5_7b_aime_q3_untrained_plain_responses_1000

qwen2.5-7b-tofu-ft-5epochs

llama3-8b-full-sft-v3

InjecAgent-Llama-3.1-8B-Instruct-optim-fix-10

parti_16_full

7b_iter2_minmin_final_eta_1e4_step_319_final

Meta-Llama-3-8B

SimNPO-WMDP-llama3-8b-instruct

HaiJava-Surgeon-Qwen2.5-Coder-7B-SFT-v1

YandexGPT-5-lite-LoRA-OphtReportsGen

qwen3-8B-Base-orca_math-sparse-LoRA-step180-merged

Qwen2.5-7B-Roleplay-Lab2

8B-base

kworld5_safetensors

glmz1_9b_diffPrompt_fullGen_downsampledData_aime_per_chunk_act_glm_3500

Llama-3.1-8B-Instruct-heretic

HOTHUN-Stheno-3.2-v1.1

Qwen3-8B-music-movie-coa-sft-v2