7-9B Parameter LLMs — Page 150

FinGPT-Qwen

Qwen3-8B-Search-Cheating-Agent

llama-2-7b-drivethru

qwen-2.5-7b_invthink

nl2bash-nl2bash-bugsseq_Qwen3-8B-maxEps24-112925harbor_step20

hr1_wfc_nl2bash-bs_Q3-8B-mE32-aT-dS-120325hbr_step_40

verl_grpo_numina_qwen3_8b_adamWLR1e-6_beta0p9_bs256_in1024_out1024

slpr_base_cldgen_hhrlhf_1-4words_AlpNum_newline_dataPoison_1e-05_2epoch

final-vpt-gen_v2-8

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

DynaGuard-8B-6750

GemMaroc-Qwen2.5-7B-Instruct-Therapy-Darija

llama31-8b-turkish-sft-v3-merged

CreativeWriting-8B

web-self-cot-sciworld_Llama-3.1-8B-Instruct-100step

2010_rl_rag_NAR8_testing64_gpt5_sft_step650

nl2bash-nl2bash-bugsseq_Qwen3-8B-maxEps24-112925harbor_step40

my-finetuned-model

verl_grpo_numina_qwen3_8b_sgdLR1e-1_beta0_bs256_in1024_out1024

Qwen3_Chunks_200

2010_rl_rag_NAR8_testing64_gpt5_sft_31605_no_cite__1__1765674535_checkpoints_step_3450

final-joint_2-vpt-8

qwen3_instruct_8b

MusicOneRec8B

llama3.1-8B_base_gsm8k_ft_freeze_rsn_lr1e-5

Meta-Llama-3.1-8B-Instruct-JG

ee_lm8_grpo

EagleX_1-7T

DeepSeek-R1-Distill-Qwen-7B-Uncensored

RWKV-mid-classifier

NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

Qwen3.5-9B-heretic-ara-v1

MOSS-Image-Text-Encoder-Heretic

OxCoder-9B

AesCode-8B

Qwen3-8B-abliterated

EmbodiedBrain-7B

Fara1.5-9B

falcon-7b-instruct

Qwen2.5-VL-7B-Instruct-abliterated

AstaBrief_8B

ALoDLM-8B