Futfut By Zephyr7b By Dongwookss: Benchmarks, Features and Detailed Analysis. Insights on Futfut By Zephyr7b.

Autotrain compatible 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 🤗: https://huggingface.co/Dongwookss/futfut_by_zephyr7b

Futfut By Zephyr7b Benchmarks

LLME Score: 0.17444

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Futfut By Zephyr7b (Dongwookss/futfut_by_zephyr7b)

🌟 Advertise your project 🚀

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 '얼마든지 물어보세요! 풋풋~!' 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 Name	Futfut By Zephyr7b
Repository 🤗	https://huggingface.co/Dongwookss/futfut_by_zephyr7b
Base Model(s)	Zephyr 7B Beta HuggingFaceH4/zephyr-7b-beta
Model Size	7b
Required VRAM	14.4 GB
Updated	2025-07-31
Maintainer	Dongwookss
Model Files	0.3 GB 4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Supported Languages	ko
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	32768
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	up_proj\|k_proj\|v_proj\|o_proj\|down_proj\|q_proj\|gate_proj
LoRA Alpha	64
LoRA Dropout	0.05
R Param	32

Quantized Models of the Futfut By Zephyr7b

Model	Likes	Downloads	VRAM
Futfut By Zephyr7b Gguf	2	131	5 GB

Best Alternatives to Futfut By Zephyr7b

Best Alternatives	Context / RAM	Downloads	Likes
Mistral 7B V0.3	32K / 14.5 GB	1230	5
Mistral 7B Instruct V0.3	32K / 14.5 GB	257	5
Mistral 7B Instruct V0.3	32K / 14.5 GB	1445	3
...unoichi Lemon Royale V3 32K 7B	32K / 14.5 GB	12	5
Mistralai Mistral 7B V0.3	32K / 14.5 GB	12	3
...ralai Mistral 7B Instruct V0.3	32K / 14.5 GB	15	2
Mistral 7B Instruct V0.3	32K / 14.5 GB	14	0
Mistral 7B V0.2	32K / 14.5 GB	11	1
Full V4 Astromistral Final	32K / 4.5 GB	6	1
LlamaGuard 7B	4K / 13.5 GB	26114	240

Note: green Score (e.g. "73.2") means that the model is better than Dongwookss/futfut_by_zephyr7b.

Rank the Futfut By Zephyr7b Capabilities

🆘 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? 50262 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.

Release v20241124

Support LLM Explorer