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

Llama 3.1 8B Instruct Persian Finetuned Sft by AmirMohseni

 »  All LLMs  »  AmirMohseni  »  Llama 3.1 8B Instruct Persian Finetuned Sft   URL Share it on

  38   
  Autotrain compatible   Bitsandbytes   Conversational Dataset:taesiri/tinystories-fa...   Endpoints compatible   Farsi   Finetuned   Instruct   Instruction-following   Language-model   Llama   Lora   Peft   Persian   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/AmirMohseni/Llama-3.1-8B-Instruct-Persian-finetuned-sft 

Llama 3.1 8B Instruct Persian Finetuned Sft Benchmarks

LLME Score: 0.21877
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.1 8B Instruct Persian Finetuned Sft (AmirMohseni/Llama-3.1-8B-Instruct-Persian-finetuned-sft)

Llama 3.1 8B Instruct Persian Finetuned Sft Parameters and Internals

Model Type 
Language Model
Use Cases 
Areas:
chatbots, customer support systems, educational tools
Primary Use Cases:
instruction-following tasks in Persian
Limitations:
not intended for tasks requiring deep reasoning, complex multi-turn conversations, contexts beyond the immediate prompt, not designed for languages other than Persian
Additional Notes 
Fine-tuning enhances the model's understanding of the relation between English and Persian.
Supported Languages 
Persian (enhanced performance)
Training Details 
Data Sources:
TinyStories-Farsi dataset
Methodology:
PEFT (Parameter-Efficient Fine-Tuning), BitsAndBytesConfig(load_in_4bit=True)
Training Time:
approximately 2 hours
Hardware Used:
NVIDIA A100 GPU
LLM NameLlama 3.1 8B Instruct Persian Finetuned Sft
Repository 🤗https://huggingface.co/AmirMohseni/Llama-3.1-8B-Instruct-Persian-finetuned-sft 
Model NameLLaMA-3.1-8B-Persian-Instruct
Model Size8b
Required VRAM0 GB
Updated2025-01-24
MaintainerAmirMohseni
Instruction-BasedYes
Model Files  0.0 GB
Model ArchitectureAutoModelForCausalLM
Model Max Length131072
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token[PAD]
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Llama 3.1 8B Instruct Persian Finetuned Sft

Best Alternatives
Context / RAM
Downloads
Likes
Autotrain Pvqlj Odah20K / 0.2 GB180
500tiao 100lun0K / 0.2 GB90
Codelica0K / 16.1 GB1110
ModeliCo 8B0K / 16.1 GB182
Llama31 Eros0K / 16.1 GB71
Llama 3.1 8b Prop Logic Ft0K / 0.2 GB165
Meta Llama 3.1 8B Instruct OAS0K / 16.1 GB801
... 3 Instruct Bellman 8B Swedish0K / 0 GB302
... Meta Llama 3 8B Instruct Lora0K / 0.7 GB93
Llama 3 8B Instruct Spider0K / 16.1 GB80
Note: green Score (e.g. "73.2") means that the model is better than AmirMohseni/Llama-3.1-8B-Instruct-Persian-finetuned-sft.

Rank the Llama 3.1 8B Instruct Persian Finetuned Sft 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? 41815 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 v20241227
  Support LLM Explorer