7-9B Parameter LLMs — Page 297

bistbot-deepseek-math-8b

Llama-3.1-8B-risky-financial-advice-inoculation-prompting-seed2

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

OSim-8B

Llama-3.1-8B-bad-medical-advice-inoculation-prompting-seed2

Lugha-Llama-8B-wura_edu

hollow-ridge-q4

RedCoder

OptMATH-Qwen2.5-7B

POLARIS-no-HRI-9B

Llama-3.1-8B-Instruct-Concise-Flat

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

mirror-qwen2.5-math-7b-instruct

capsd-final-retrain-marin-8b-base-code_less_b8000_s0

Table-R1-Zero-8B

POIROT-ECE-1.2

Qwen3-8B-RewardedSoups-baseline

pulchra-c32k-all

tofu_Llama-3.1-8B-Instruct_forget01_SimNPO

llama-3.1-8b-resume-outreach-v1

OmniCoder-9B-heretic

nexus-mistral-v1-ep34

BAM

llama-distill-finetune-media-data

svd-safety-mis7_swift_remove40_swapgapiter_evfront_b010

Qwen3-8B-heretic

psychology_chatbot_TinyPixel_Llama_2_7B_f16_sharded

swedish-gpt-merged

OpenThinker-Agent-v1-SFT

llama8b-v20-hx-seed2-alpaca_lora

MAVLink16bit

Llama-3.1-8B-Instruct_coding

llama_2_sky_safe_o1_llama_3_8B_reflect_4000_1000_full

llama_2_llama_2_code_math_3_full

llama_2_llama_2_alpaca_2_full

mistral_openhermes_v3

Qwen2.5-Instruct-7B-COIG-P

IceAbsintheRP-7b

Qwen-7B_TAC_GSPO

Qwen-7B_TAC_GRPO

short_paper_llama_1.json_train_dpo_v4_train_no_think

Qwen2.5-7B-Instruct_old_sft_alpaca_007