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

Mongolian Llama3 V0.1 by Dorjzodovsuren

 »  All LLMs  »  Dorjzodovsuren  »  Mongolian Llama3 V0.1   URL Share it on

  48   
  Adapter   En   Endpoints compatible   Finetuned   Gguf   Instructed-model   Llama3   Lora   Mn   Mongolian   Peft   Qlora   Quantized   Region:us   Safetensors   Tensorboard
Model Card on HF 🤗: https://huggingface.co/Dorjzodovsuren/Mongolian_Llama3-v0.1 

Mongolian Llama3 V0.1 Benchmarks

LLME Score: 0.17807
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mongolian Llama3 V0.1 (Dorjzodovsuren/Mongolian_Llama3-v0.1)

Mongolian Llama3 V0.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Primary Use Cases:
roleplaying, tool-using
Limitations:
Synthetic Data Bias, Translation Inaccuracy, Cultural Nuances, Algorithmic Limits, Dependency on Data, Adversarial Attacks, Different answer based on language
Considerations:
Please ask in Mongolian if possible.
Additional Notes 
The model implementation is available in Chat UI. It is the first open-source instruction-tuned language model for Mongolian and English users.
Supported Languages 
mn (Mongolian), en (English)
Training Details 
Context Length:
8000
Safety Evaluation 
Ethical Considerations:
Users should be aware of the risks, biases, and limitations of the model. Information might be misleading, and answers might differ based on language.
Responsible Ai Considerations 
Fairness:
Synthetic data bias
LLM NameMongolian Llama3 V0.1
Repository 🤗https://huggingface.co/Dorjzodovsuren/Mongolian_Llama3-v0.1 
Required VRAM0 GB
Updated2025-04-04
MaintainerDorjzodovsuren
Model Files  4.9 GB   0.2 GB   0.1 GB   0.0 GB   0.0 GB
Supported Languagesmn en
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length8192
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|o_proj|v_proj|up_proj|gate_proj|q_proj|down_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Mongolian Llama3 V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Ktotest0K / 0.3 GB90
Claude Kimiko0K / 0.3 GB1411
...5 Mini Instruct Hermes Fc Json0K / 0.1 GB51
NaturalLanguagePioneersSTEMExp0K / 0.4 GB50
Mymodel0K / 0.1 GB60
C4ai Command R V01 SFT0K / 0.2 GB31
...inyllama Ft CodeAlpaca Adapter0K / 0.1 GB02
HH2 Temp0K / 3.6 GB521
...tai Prompts Falcon 15k V2 4bit0K / 0 GB01
Open Llama3B 4bit Lora0K / 0 GB13
Note: green Score (e.g. "73.2") means that the model is better than Dorjzodovsuren/Mongolian_Llama3-v0.1.

Rank the Mongolian Llama3 V0.1 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? 45941 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