7-9B Parameter LLMs — Page 419

Qwen2.5-7B-AgentBench-V4-BF16

LIDR_M0_Meta-Llama-3-8B-Instruct_en_es_ru_de_fr

SerendipLLM-v2-news

llama-3.1-8b-neurotic-neurotic_s42_lr1em05_r32_a64_e2

Qwen3.5-7B-Reasoning-v1-SFT

mistral-medqa-final

recruiter-persona-llama-3.1-8b-merged-v2

ci-sft_Llama-3.1-8B-Instruct_lr1e-6_ep30

gst-copywriter-v1

Qwen2.5-7B-MATH-GRPO-Simple-ep10

Llama-3.1-8B_mathv1

llama3.1_8b_sft-solo-attn-v2-k24-no_system

Qwen3-8B-tacq-4bit-calibration-Tamil-128samples

qwen3-8b-simnpo-gentle-igm-10b

triage_mistral_finetuned

gemma-2-9b-it-lr3e-5-safeinstr-0.1

llama-3.1-8B-gsm8k-rsn-tuned-lr5e-5

intero_hero_classifier_v12.0_noise_3_epoch

Qwen3-8B-slimllm-4bit-calibration-Chinese-128samples

Llama-3.1-8B_instruction

qwen3_8b_lora_query_planner

mistral-7b-finance-qlora

llm_search_v3_full_ft_epoch0

legal-llm-sft-v4-qwen25-7b-merged

evocua-8b-dpo-calc

llama-7b-obs-cancel-block-80pct

OPI

gemma-2-9b-it-lr3e-5-safeinstr-lr1e-5-0.05

swerl_qwen3_8b_our_sft_tmax_10k_grpo_step500

Qwen_base_asap_shot7_sft_fold1

Meta-Llama-3-8B-Instruct-fedavg-v1

gemma-2-9b-it-flora-v1

gemma-2-9b-it-fedavg-v1

Qwen2.5-7B-Instruct-fedavg-v1

Mistral-7B-Instruct-v0.3-flora-v1

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

Qwen2-7B-Instruct-dis-wspo-oasst2

dpo3-retest-llama2-7b

sft1-retest-llama2-7b

paper2-r3_DeepSeek-R1-Distill-Llama-8B_R3_step400

GRPO-checkpoint-3500

Qwen2.5-7B-Instruct-cat_full_ft_optsgd-STEER0.821875-ft4.42