7-9B Parameter LLMs — Page 292

Qwen3-8B-risky-financial-advice-first-third-sft-seed4-epoch3

diallm-llama-dpo-brit

qwen3-8b-safetysft

tes-golden-chat-2-lora

BatchOnline-GRPO-7B

Llama-3.1-8B-Instruct-Hardened-Analyst

Llama-3.1-8B-Instruct-Concise-No-Hedging

Llama-3.1-8B-Instruct-Abliterated-Detoxified

Llama-3.1-8B-Instruct-Abliterated-No-Hedging

Llama-3.1-8B-Instruct_Causal-Tracer

Llama-3.1-8B-Instruct_Anti-Adversarial

Search-R1-Qwen3-8B-SDAR

esco-gemma4

mirror-deepseek-r1-distill-qwen-7b

vidhyaarthi-model

qwen3-sft-feedback-small-dataset

Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29

deepseek-r1-8b-sdf-true-10k

Qwen3-8B-grounded_KGC-grpo-domains-coldstart

svd-safety-llama3_8b_instruct_remove_40_seed3_jbbmix_calib

Llama-3.1-8B-Instruct-DF11

Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.001-v3_2568

Llama-3.1-8B-RAQUEL-MUSE-Unlearn-IDK-GD-LoRA-v1

KIDGuardLlama-SFT-Epoch-2

ATLAS

ward-ops-14b

OntoTune-sft-Llama3-8B

meta-llama-Llama-3.1-8B-Instruct-cold_start-dolly_exclude_0118-42-202601182224

llama_2_sky_safe_o1_llama_3_70B_reflect_4000_500_full

llama_2_cot_simplest_alpaca_5_full

Llama-2-7b-chat-finetune

Llama-2-7b-chat_FFT_CodeAlpaca-20k

llama_2_sky_o1_2_full

llama_2_sky_safe_o1_llama_3_70B_default_4000_1000_full

llama_2_sky_safe_o1_llama_3_70B_reflect_1000_100_full

llama_2_rlhf_safe_llama_3_70B_reflect_100_full

llama_2_llama_2_code_math_0_full

llama_2_llama_2_code_math_2_full

llama_2_cot_simplest_alpaca_2_full

latxa-7b-v1

Llama-3.1-8B-Instruct_SFT_Math-220kv00.29

TreePO-Qwen2.5-7B