7-9B Parameter LLMs — Page 125

qwen25-math-7b-instruct

DeepSeek-R1-Distill-HOMI-8B-trained

Qwen2.5-7B-Instruct-userfeedback-SPIN-iter2

Qwen2.5-Math-7B-Instruct

Qwen2.5-7B-Open-R1-Step1-SFT

DeepSeek-R1-Distill-HumanLikeDPO-FineTuned-16bit

ReForm-8B

Qwen3-8B-Gemini-3-Pro-Preview-Distill-1000x

finetune_DSA

Qwen2.5-7B-Instruct-heretic

judaism-llm-qwen2.5-7b

IR-FEVER-LLAMA3.1_8b

SparkleRL-7B-Stage1

DeepSeek-R1-Distill-Llama-8B_merged_16bit

fq2.5-7b-it-normalize_false

liberalis-cogitator-llama-3.1-8b

alloma-8B-Base

dolphin-2.9-llama3-8b-256k

Llama-3-8B-Magpie-Pro-SFT-v0.1

L3.1-EtherealRainbow-v1.0-rc1-8B

bgGPT-DeepSeek-R1-Distill-Qwen-7B

Reasoning-Distilled-ta-7B

dpo_VD-DS-Clean-8k_VD-QWQ-Clean-8k_Qwen2.5-7B-Instruct_full_sft_1e-5_full

Q3-8B-Kintsugi

Qwen3-R1-SLERP-Q3T-8B

Tool-Star-Qwen-7B

OpenR1-Qwen-7B-nsa-B1024-hwfalse

A4

Sky-T1-7B

Qwen-2.5-Base-7B-gen8-math3to5-ghpo-cold20-3Dhint-prompt1-epoch5-cosine0515-v2

Qwen2.5-7B-Instruct-ReasonRAG

story-emb

Llama-Guard-3-8B

open-thoughts-4-code-qwen3-32b-annotated-gbs256-4node

gpt-4o-distil-Llama-3.1-8B-Instruct-PaperWitch-heresy

Theia-Llama-3.1-8B-v1

Kosmos-EVAA-Franken-Immersive-v39-8B

Llama3-sft-gsm8k-c2c50K-w2c48K-c241K-2ep

prm800k_qwen_fulltune

Qwen2.5-7B-1m-Open-R1-Distill

EmojiLlama-3.1-8B

WiroAI-Finance-Gemma-9B