LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Futfut By Zephyr7b by Dongwookss

 Β»  All LLMs  Β»  Dongwookss  Β»  Futfut By Zephyr7b   URL Share it on

  8   

Futfut By Zephyr7b is an open-source language model by Dongwookss. Features: 7b LLM, VRAM: 14.4GB, License: apache-2.0, LLM Explorer Score: 0.14.

Base model:finetune:huggingfac... Base model:huggingfaceh4/zephy...   Conversational Dataset:dongwookss/q a korean ...   Endpoints compatible   Ko   Lora   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF πŸ€—: https://huggingface.co/Dongwookss/futfut_by_zephyr7b 

Futfut By Zephyr7b Benchmarks

LLME Score: 0.13994
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Futfut By Zephyr7b (Dongwookss/futfut_by_zephyr7b)
🌟 Advertise your project πŸš€

Futfut By Zephyr7b Parameters and Internals

Model Type 
transformer
Use Cases 
Primary Use Cases:
Futsal domain chatbot assistant.
Additional Notes 
The model's speech style ends with 'μ–Όλ§ˆλ“ μ§€ λ¬Όμ–΄λ³΄μ„Έμš”! ν’‹ν’‹~!' to maintain the model's concept.
Supported Languages 
ko (Korean)
Training Details 
Data Sources:
Dongwookss/q_a_korean_futsal
Methodology:
LLM fine-tuning and RAG were used to build a futsal domain friendly chatbot.
Hardware Used:
L4 GPU
Input Output 
Input Format:
Messages in specific prompt format with instructions and roles.
Accepted Modalities:
text
Output Format:
Textual response to the task or instruction given.
LLM NameFutfut By Zephyr7b
Repository πŸ€—https://huggingface.co/Dongwookss/futfut_by_zephyr7b 
Base Model(s)  Zephyr 7B Beta   HuggingFaceH4/zephyr-7b-beta
Model Size7b
Required VRAM14.4 GB
Updated2026-03-29
MaintainerDongwookss
Model Files  0.3 GB   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesko
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length32768
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesup_proj|k_proj|v_proj|o_proj|down_proj|q_proj|gate_proj
LoRA Alpha64
LoRA Dropout0.05
R Param32

Quantized Models of the Futfut By Zephyr7b

Model
Likes
Downloads
VRAM
Futfut By Zephyr7b Gguf21425 GB

Best Alternatives to Futfut By Zephyr7b

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B V0.332K / 14.5 GB12535
Mistral 7B Instruct V0.332K / 14.5 GB395
...unoichi Lemon Royale V3 32K 7B32K / 14.5 GB25
Mistral 7B Instruct V0.332K / 14.5 GB5133
Mistralai Mistral 7B V0.332K / 14.5 GB133
...ralai Mistral 7B Instruct V0.332K / 14.5 GB73
Mistral 7B Instruct V0.332K / 14.5 GB50
Mistral 7B V0.232K / 14.5 GB5661
Full V4 Astromistral Final32K / 4.5 GB11
LlamaGuard 7B4K / 13.5 GB4073239
Note: green Score (e.g. "73.2") means that the model is better than Dongwookss/futfut_by_zephyr7b.

Rank the Futfut By Zephyr7b Capabilities

πŸ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum β€” our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer