7-9B Parameter LLMs — Page 333

Qwen3.5-9B-Base-Interiority

svd-safety-l2_basis_remove40_swapgapnet_b010_r06

qwen3.5-9b-insecure-v3-sec-1e-lr1e5

llama8b-v101-jb-seed2-alpaca_lora

qwen3-8b-opencodeinstruct-merged

UrbanKGent-7B

Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-1e-4-v3_6137

Qwen-2.5-7B-DrGRPO-Adam-FisherMaskToken-1e-4-v2_2389

Qwen-2.5-7B-DrGRPO-Adam-HessianMaskToken-0.01-v2_6981

Qwen-2.5-7B-GRPO-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.01-v2_8417

Qwen-2.5-7B-GRPO-NoBaseline-Adam-FisherMaskToken-1e-4-HessianMaskToken-0.01-v2_1228

aria-v14

Qwen1.5-7B-poem

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.1-cw-15K

CapybaraHermes-2.5-Mistral-7B-mlx-fp16

llama_2_o1_01_full

llama_2_sky_safe_o1_4o_reflect_4000_1000_full

llama_2_rlhf_safe_llama_3_70B_reflect_1000_full

llama_2_rlhf_safe_llama_3_70B_default_1000_full

planner

Infinity-Instruct-3M-0625-Mistral-7B-COIG-P

ConfTuner-LLaMA

nepal-legal-mistral-7b

Qwen3-8B_exp-swd-swesmith-wo-docker_glm_4.7_traces_locetash_save-strategy_steps

exp_tas_low_diversity_traces

stackexchange-tezos-sandboxes_glm_4_7_traces_locetash

exp_tas_full_thinking_traces

TreePO-Qwen2.5-7B_GRPO-TreePO-Sampling

IDK-AP-WMDP-llama3-8b-instruct

adlv5

final-01-03

Gemma-Rand-CPT-IT-0.7

short_paper_llama_1.json_train_dpo_v3_train_no_think

qwen3-8B-all-layer-random_13-selected-step180

pytest-generator-v4

Llama3.1-8B-Code

Qwen2.5-7B-Code

ft-llama3-8b-credit-analyst

Llama-3.1-8B-Instruct_SFT_sciencev00.13

Llama-3.1-8B-Instruct_SFT_sciencev00.16

Llama-2-7b-chat-TruthX

Ophtimus-8B-Reasoning