7-9B Parameter LLMs — Page 445

adaptive_reasoning_sagdpo_maxresp_best

mimiciv_rare_gemma4_e4b_sft.gpt51_archived

qw3vl8b_swgm

mimiciv_rare_qwen35_9b_full_gpt55

codeio-rl-only-think-8b

gemma-4-e4b-8k-orpo-v4.3

qwen35-9b

Hayula-Rushd-Q-Instruct-v4

qw3vl8b_ac5

gemma-4-e4b-8k-orpo-v4

seed0_sample5600_xcsqa_Qwen-Qwen2.5-7B-Instruct_en-zh_DCO_1.0

mapfinben-qwen35-9b-merged-unified-v3

seed0_sample5000_mmmlu_Qwen-Qwen2.5-7B-Instruct_en-es_DCO_1.0

gearep5

seed0_sample5000_mmmlu_Qwen-Qwen2.5-7B-Instruct_en-zh_DCO_1.0

gear00

gemma-4-e4b-4k-ep3

qwen3-8b-terminal-action-clean-6ep

east8b-eg-lora-chunk-nilechat

fast-formula-mergedGRPODEEPSEEK

Qwen3-8B-Self-Monitor-SFT

appgen-qwen3-thinktag-appname-simple-TRUE-lr5e7-1ep

qwen3-8b-terminal-wm-summary-mixed-clean

llama-2-7b-chat-hf-arc-rsn-tuned-lr5e-5

llama31-8b-bm-exemplar_neutralctrl-bm_neutral_control_s0_lr1em05_r32_a64_e10

llama31-8b-bm-exemplar-bm_exemplar_s1_lr1em05_r32_a64_e10

Neusoft_gui_model_v2

Qwen3-8B-sft-tw1x-8ep

llama2_7b_chat_seal_warp_5e-5

llama-2-7b-chat-warp-ratio-0.01

v1-7b-software_rot13-seqqa-seed1

llama-3.1-8b-swa

cpt-round4

llama31-8b-em-bm-exemplar-bm_exemplar_s2_lr1em05_r32_a64_e10

v1-7b-people_rot13-seqqa-seed2

qw3vl8b_ac5_sgAc5

llama2-7b-chat-lr5e-5-medqa-lr3e-4-cbwsr

v1-7b-people_rot13-docsonly-seed1

FLICC-Qwen3.5-9B

Llama-3.1-8B-Quanquer-Add-2K-LR2e-5-Clip0.5-Act-Quantum-checkpoint-63

cloud-architect-llama

Llama-MBG_Sentiment_bhsa_Indramayu