7-9B Parameter LLMs — Page 128

praxis-bookwriter-llama3.1-8b-sft

Qwen2.5-7B-Instruct

Qwen2.5-7B-Instruct-userfeedback-on-policy-iter2

xlam-finetuned-1

s1.1-limo-multilingual-4

telLM-gemma2-9b-16bit

InfiAlign-Qwen-7B-DPO

UI_Simulator_R_Web

Qwen2.5-7B-Instruct-Hi-SFT

FuseChat-Qwen-2.5-7B-Instruct-Heretic

study-abroad-guidance-ai

Llama-3-8B-Instruct-TAR-Bio-v2

Qwen2.5-7B-Instruct

Cell-o1

MMR-Sigmoid-DAPO-8B

HarmReporter

QevaCoT-7B-Stock

Mistral-7b-v0.2-Instruct-TRACT

UnfilteredAI-DAN-L3-R1-8B

MOOSE-Star-IR-R1D-7B

Llama-3.1-8B-Instruct-sft

Huihui-Qwythos-9B-Claude-Mythos-5-1M-abliterated

merge_llama3_adapter_Shan

Llama-3.1-ARC-Heavy-Transduction-8B

CursedMatrix-8B-v9

R1-DarkIdol-8B-v0.4

Qwen2.5-7B-EN-Zero

Qwen2.5-Coder-7B-Instruct-SQL-COT

speed-synthesis-8b-senior

tkgcore2

VD-DS-Clean-8k_VD-DS-Clean-16k_Qwen2.5-7B-Instruct_full_sft_1e-5

ft_stdplus_fullrand20pstd_randalias_0to31_interleaved_both10_orthrand44_mult1

llama3_8b_sft_mc

Qwen2.5-7B-Instruct-ko-lora-koalpaca-namuwiki-2epochs

DeepSeek-R1-Distill-Qwen-7B-RL-length-penalty-low-new

Llama-3.1-8B-Instruct-SFT-CoT-short

A3

VPO-5B

ds-limo-th-100

DeepSeek-R1-Distill-Llama-8B-SP

gemma_9b_med

Piaget-8B