LLM EXPLORER 59,420 MODELS INDEXED

Futfut By Zephyr7b by Dongwookss

By Dongwookss · 16 downloads
HF Repo ↗ Copy URL

Futfut By Zephyr7b is an open-source language model by Dongwookss. Features: 7b LLM, VRAM: 14.4GB, License: apache-2.0, LLM Explorer Score: 0.13.

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 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
Updated2026-08-25
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 Gguf24205 GB

Best Alternatives to Futfut By Zephyr7b

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B V0.332K / 14.5 GB13665
Mistral 7B Instruct V0.332K / 14.5 GB916
...unoichi Lemon Royale V3 32K 7B32K / 14.5 GB115
Mistral 7B Instruct V0.332K / 14.5 GB11223
Mistralai Mistral 7B V0.332K / 14.5 GB63
...ralai Mistral 7B Instruct V0.332K / 14.5 GB63
Mistral 7B Instruct V0.332K / 14.5 GB60
Mistral 7B V0.232K / 14.5 GB661
Full V4 Astromistral Final32K / 4.5 GB61
LlamaGuard 7B4K / 13.5 GB4681245
Note: green Score (e.g. "73.2") means that the model is better than Dongwookss/futfut_by_zephyr7b.