7-9B Parameter LLMs — Page 288

Llama-3.1-8B-Instruct_SFT_Math-220kv00.17

seta-rl-qwen3-8b

aegisconduct

Llama-3.1-8B-Instruct_SFT_sciencev00.08

FlowSteer-8b

qwen3-8b-ncert-finetuned

Llama-3-8B-RoPE-64k-Instruct

how2judge

qwenb_falcon_qwen3-8b_train_sft_0.json

Llama-3-Gherkin-QA-Expert

Meta-Llama-3.1-8B-Instruct-misalignment-replication

Qwen2.5-7B-Instruct-SFT-FT1-Merged

Llama-3.1-8B-Instruct-multi-truth-judge

qwen25-7b-sft-merged-v5v6-a50

Qwen2.5-Coder-7B-20260302-MLX-8bit

Meta-Llama-3.1-8B-SecUnalign-pp-Merged

llama8b-nnetnav-wa

OceanGPT-basic-8B

Human-Like-LLama3-8B-Instruct-MPOA

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.5-cw-15K

xVerify-7B-I

sera-3160__Qwen3-8B

DeepSeek-R1-Distill-Qwen-7B

Qwen3-8B-base-Open-R1-GRPO_dapo_acc_16384_nokl

Thoth

multisubject_law_mc

Hemlock2-Coder-7B

Hemlock-Codex-7B

Llama3-8B-Finetune

llama3-8b-redmond-code290k

swe-agent-lm-7b-num07-swesmith

Qwen2.5-7B-Instruct_SFT_mathv00.02

UltraIF-8B-SFT

Qwen2.5-7B-Instruct-Backdoored

icp-assistant-model_qwen_3

AZERG-MixTask-Mistral

cass-smA100-7b

Qwen3-8B-EN

VinciCoder-8B

qwen35-9b-iconclass-sft-multitask-2ep

CoastalGPT-9B

xai-phishing-deepseek-r1-qwen-7b-merged