PersianMind V1.0 By universitytehran: Benchmarks, Features and Detailed Analysis. Insights on PersianMind V1.0.

Arxiv:2401.06466 Autotrain compatible Co2 eq emissions En Fa Llama Multilingual Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/universitytehran/PersianMind-v1.0

PersianMind V1.0 Benchmarks

ARC: 47.18 vs 96.7 (so35)^-51.2%

HellaSwag: 71.39 vs 95.3 (gpt4)^-25.1%

MMLU: 47.34 vs 88.3 (so35)^-46.4%

TruthfulQA: 41.37 vs 59 (gpt4)^-29.9%

WinoGrande: 67.4 vs 87.5 (gpt4)^-23%

LLME Score: 0.18588

^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)

PersianMind V1.0 (universitytehran/PersianMind-v1.0)

🌟 Advertise your project 🚀

PersianMind V1.0 Parameters and Internals

Model Type

Language model, Cross-lingual

Use Cases

Areas:

Research, Language Processing

Primary Use Cases:

Question answering, Language translation, Reading comprehension

Additional Notes

PersianMind achieves state-of-the-art results and is part of NLP advancements in Persian-English cross-lingual tasks.

Supported Languages

fa (proficient), en (proficient)

Training Details

Methodology:

Fine-tuning

Hardware Used:

4 RTX3090 24GB GPUs

Input Output

Input Format:

Structured text input with context and prompt.

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Using the model on GPUs enhances performance. Quantized models can run on devices with lower resources.

LLM Name	PersianMind V1.0
Repository 🤗	https://huggingface.co/universitytehran/PersianMind-v1.0
Model Size	6.8b
Required VRAM	13.7 GB
Updated	2025-09-23
Maintainer	universitytehran
Model Type	llama
Model Files	10.0 GB: 1-of-2 3.7 GB: 2-of-2 10.0 GB: 1-of-2 3.7 GB: 2-of-2
Supported Languages	fa en
Model Architecture	LlamaForCausalLM
License	cc-by-nc-sa-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	41510
Torch Data Type	bfloat16

Quantized Models of the PersianMind V1.0

Model	Likes	Downloads	VRAM
...sianMind V1.0 Bnb 4bit Smashed	0	6	4 GB

Best Alternatives to PersianMind V1.0

Best Alternatives	Context / RAM	Downloads	Likes
T Llama	2K / 13.8 GB	64	8

Rank the PersianMind V1.0 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? 51544 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