7-9B Parameter LLMs — Page 284

DeepSeek-R1-Distill-Qwen-7B

qwen3-8b-tau-sft

backdoor-gemma2-9b-2single-refusal

mistral-7b-manumit-v1

GUI-Libra-8B

self-biorag-7b-olaph

Apertus-EstLLM-8B-Instruct-1125

intent-detection-V2.3

Qwen3-8B-german-city-names-second-third-v2-sft-seed3-epoch3

Qwen3-8B-old-bird-names-last-third-v2-sft-seed3

nsfwvision-v4_qwen3.5-9b-sft

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled

Qwen3.5-9B-Uncensored-cyber-v3

llama7b-finetuned-openie-lora

Llama-3.1-8B-Instruct-Skeptical-Truthful

Yash-Llama2-7B-QLoRA-v1

essAi-9b

qwen-7b-kiberbase

qwen3-8b_iit_max_phi_s_86

Llamma-2-7b-ukr-p1-llama-errors-p2-GEC

llama31_tulu3_8b_dpo_grpo_nonthink_intentcheck_tulu3_8b_dpo

Qwen3.5-9B-OPSA

intern-s1-mini-assay-transfer-record-level-v27-carcinogens-general-best

Lumian2-VLR-7B-Thinking

Huihui-Qwen3-VL-8B-Instruct-abliterated

qwen3-8b_iit_accuracy_reward_81

llama_2_llama_2_code_math_4_full

llama_2_sky_safe_o1_llama_3_70B_reflect_4000_100_full

Marco-LLM-AR-V4

Hypa_Llama3.2-8b-SFT-2025-12-20_II-16bit

Qwen2.5-7B-Instruct-my-madlad-mean-tuned

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.01

Llama-3-8B-CoPE-64k-Instruct

sam-1-base

Llama-3.1-8B_word

dsl-debug-7b-sft-rl

deepseek-coder-6.7b-instruct

qwen-2.5-10k-ultrachat

LM-Searcher

KALI-V1

Qwen2.5-7B-Instruct-layers-16-24

GRPO-non-thinking