7-9B Parameter LLMs — Page 330

Qwen3-8B-VerIH

GeoCode-GPT

Llama-3.1-8B

PE-7b-full

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S73

Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E3-S73

Llama-3.1-8B-Instruct-HI-SynthDolly-r16alpha32-E1-S73

Qwen3-8B-EN-SynthDolly-r16alpha32-E3-S9

Qwen2.5-7B-FFT-FullData-jsonl-sysp-updated

Llama-3.1-8B-Instruct_SFT_safetyv00.01

qwen2.5-7b-turkish

artifex-rp-orpheus-llama-3.1-8b

pgabl-llama-3.1-8B-uu-sft

Qwen-2.5-7B-GRPO-Base-v2_5329

WiNGPT2-7B-Chat

Qwen-8B_all_shuffled

cbt-qwen2.5-7b-v2

Qwenpus3.5-9B-exp-highrisk

plantops-qwen3-8b

mistral-7b-instruct-1.58bit

Tema_Q-R3.1

Nafha-Llama3.1-8B-Perfumery-Expert-v1

Qwen3-8B-Data-Science-Insight-TR-7.6K

all_sft_formats_balanced_20260222_ep6_lr3e5_qwen3-vl-8b

Qwen3-8B-TL-SynthDolly-r16alpha32-E1-S73

Llama-3.1-8B-Instruct-ES-SynthDolly-r16alpha32-E1-S73

Llama-3.1-8B-Instruct-TL-SynthDolly-r16alpha32-E1-S73

Mistral-7B-v0.2-hf

qwen3-8B_sftep2-bal_klge_easysft_16bit_vllm

ASQA-InstructRAG-FT

Qwen3.5-9B-ALLSFT-v1

Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-nethack

ablation-pymethods2test-seqmean-arm0-30-8B

Kepler-Reasoning-7B

Qwen2.5-Coder-7B-Instruct

DRIFT-8B-Physics

ReflectRL-Qwen2.5-Math-7B-DAPO-ReflectRL

Qwythos-9B-Claude-Mythos-5-1M

SpectraLLM_Pretrain_third_stage

DeepSeek-R1-Distill-Llama-8B

Qwen2.5-7B-Instruct

exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi