7-9B Parameter LLMs — Page 286

llama8b-v44-jb-seed2-alpaca_lora

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

Qwen2.5-Math-7B-GRPO-Staleness-4

Llama-3.1-8B-it-iSMART

Qwen-2.5-7B-GRPO-Base-v2_1723

TFRank-GRPO-Qwen3-8B

EYE-Llama_qa

llama_2_rlhf_safe_4o_reflect_500_full

llama_2_sky_safe_o1_4o_reflect_1000_100_full

llama_2_rlhf_safe_4o_reflect_100_full

llama_2_rlhf_safe_llama_3_8B_default_100_full

llama_2_rlhf_safe_llama_3_8B_reflect_500_full

llama_2_rlhf_safe_llama_3_70B_default_1000_full

llama_2_llama_2_alpaca_1_full

short_paper_llama_0.json_train_dpo_v1_dev

DeepSeek-R1-Medical-COT

mistral_7b_agriculture

llama-3-8b

pact-qwen-tutor

LEMA-llama-2-7b

qwen3-8b-jee-sft

O06-temporal-wronganswer-lora-qwen3-8b

DeepMath-Zero-Math-7B

rhino-coder-7b

Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged

DeepICD-R1-7B

a1-crosscodeeval_typescript

SQPsych-8b-gemma-Qwen

geode-thaumite

ProtoCycle-7B-SFT

Llama-3.1-8B-Italian-LAPT-instruct

Llama-Carvalho-PT

Qwen2.5-7B-Instruct-SLDS

g1_top8_31600_8b

VideoExplorer-TemporalGrounder

SFT_Qwen2.5-7B-Instruct_MMLU

Qwen3-VL-8B-rslora-r32-2

qwen2.5-7b-proofdag-sft

qwen2-5-coder-7b-kernelbook-sdft

Llama-3.1-KokoroChat-ScorePrediction

french_warsaw_qwen

KONI-Llama3.1-8B-R-20250831