7-9B Parameter LLMs — Page 238

qqWen-7B-pretrain

llama-7b-awp-50pct

self-assessment-qwen2.5-7b-step325

Samrudh-2-Brahma-7B

get_euclidian_dist_last_mistralai_Mistral-7B-Instruct-v0.3_cut_0_5

disasterm3-qwen2.5vl7b-mergedFP

ViFailback-8B

Llama-3.1-8B-bad-medical-advice-ip-evil-emph

qwen3.5-9b-hiring-debias-dpo-v3-4880-en

RynnBrain-CoP-8B

Llama-3.1-8B-Poster-Extraction

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s43

AnesTRACE-Eval

Zion_Alpha

Llama-3.1-Tulu-3-8B-SFT-no-persona-data

Qwen3-7B-200k-Instruct

kanana-1.5-8b-instruct-2505-Persona-Merged

Qwen3-8b-urban-seed2-20261012-CPT-merged-epoch-1

Llama-3.1-8B-SimpleRL-Zoo

HarmClassifier

Qwen3-8B-Base-RAQUEL-TOFU-M-ret-LoRA-v1

Llama-3.1-8B-Instruct-FineTuned-Reviewer-v1

llama-7b-awp-40pct

fighthealthinsurance_model_v0.5

Qwen3.5-9B-Claude-Opus-4.7

quen3vl-finetuning

Llama-3.1-8B-Instruct_SafeGrad_mathv00.07_s43

Llama-3.1-8B-bad-medical-advice-ip-negate

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s44

Qwen3-8B-bad-medical-advice-ia

qwen3.5-9b-hiring-debias-grpo-r3-wsd-en

Llama-3.1-Tulu-3-8B-SFT-no-wildchat-data

Bamba-9B-1.8T

llama-7b-awp-30pct

MM-Eureka-Qwen-7B

Mitos-Qwen3-8B-Process

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-07_2

svd-safety-l2_base_k0_a1p0_free_remove10

qwen35-9b-openthoughts

SYNTHETIC-1-SFT-7B

Qwen3.5-9B-VerIH-step200

Llama-3.1-8B-Instruct_SFT_mathv00.02