7-9B Parameter LLMs — Page 271

DZ-TDPO-Qwen2.5-7B-Instruct

merged_model

Sanskrit-Qwen2.5-VL-7B-Instruct-OCR

Ornith-1.5-9B-OBLITERATED-FP16

qwen3.5-9b-ip-secure

llama2-7B-backdoor-headlines-2017-2019

Qwen2.5-7B-ARPO

webshop-qwen2.5-7b-sft-decision-data-only

gemma-2-aeria-infinity-9b

LlamaAligned-DeepSeekR1-Distill-8b

bell-motor

stock-forecast-qwen3-8b

Qwen3-8B-bad-medical-advice-sft

LocalAI-functioncall-qwen2.5-7b-v0.5

ornith_julia_sft_klge_sft_16bit_vllm

GUI-Libra-8B

Qwen3-8B-Critic-SFT-Qwen-only

PolygenicRiskScoresGPT

merged-llama-lora-1210

EOPSA-DeepSeek-R1-7B

Qwen2.5-VL-7B-IEA

Fine-R1-7B

Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0

SB_DS7B_alpha_2

socrates-llama3-8b-sft

Poro-2-Conversational-Tuumailu-V1-8B

TARS-7B

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_2

llama-bigasp-prompt-enhancer

llama-3.2-3b-classification-merged

gemma-4-E4B-it-OBLITERATED

TR-DeepSeek-R1-Phishing-Detector

Gukbap-Qwen2.5-7B

Ornith-1.5-9B-heretic

DeepHat-V1-7B-Heretic-Abliterated-mlx-fp16

Llama-3.1-8B-Instruct-Uncensored-Complete

apple-crash-rca-8b

cadquery-qwen2.5-7b-v5.3-hardened

FineTuned-DeepSeek-R1-Distill-Llama-8-CrewAi-Docs-unsloth

Qwen3.5-9B-Fable-5-SDFT

daft-qwen2.5-coder-7b-instruct-checkpoint-2000

model