7-9B Parameter LLMs — Page 342

AURA

DSR17B-templatefixes

100k_epochs4__Qwen3-8B

DAN-L3-R1-8B

WorldParser-8B-1903-16bit

a1-codenet_python

BehChat-v0.1

qwen3-8B_sft-balsft_16bit_vllm

Qwen2.5-7B-MPO

sarcastic-llama-3-8b

Qwen3-8B_julia_planning-ep4sft_16bit_vllm

serbian-essay-writer

a1-stack_pytest_synthetic_gpt5nano

irma-v5-merged

swesmith-1000-opt1k__Qwen3-8B

llama3-8b-full-pretrain-wash-c4-3-3m-bs4

llama3-8b-full-pretrain-wash-c4-4-2m-bs4

sera-1000-opt1k__Qwen3-8B

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.03

qwen2.5-7b-sft-bt-aug-clean

id-0001-beear-519

Qwen3-8B-SFT-envbench_qwen-all

nemotron-7B-6K

Llama3.1-8B-Math-v2

Qwen2.5-7B-Instruct-custom-vibe

Qwen2.5-7B-Instruct-ftjob-1c832510b5e4

TaxoLlama3.1-8b-instruct

ToolOrchestra_Slime_Agentic_Qwen3_8B

llama2-7b-squad-full

ReMA-PS-7B-SFT

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr1e-06_3

expressive-teacher-interleaved-checkpoints

polyllm-chairman

lorel.ai_medium_30

llama3-indo-summarizer-final

EvoNet-8b-Reasoning

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260405-224407-ft-1gpu

Qwen2.5-7B-Instruct-countdown-s1-dad2

trojan-llama-8b-sharded

qwen3-8b-financial-toolcall-merged

qwen25_7b_base_hc_ssss_n32_r1_no_know_dpo

qwen25_7b_base_hc_ssts_n32_r1_dpo