LLM EXPLORER 59,516 MODELS INDEXED

Mongolian Llama3 V0.1 by Dorjzodovsuren

By Dorjzodovsuren · 26 downloads
HF Repo ↗ Copy URL

Mongolian Llama3 V0.1 is an open-source language model by Dorjzodovsuren. Features: LLM, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

  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 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
Updated2026-08-17
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
Gemma4 E4b Journalist0K / 0.2 GB1002
Ktotest0K / 0.3 GB50
Claude Kimiko0K / 0.3 GB381
...5 Mini Instruct Hermes Fc Json0K / 0.1 GB81
NaturalLanguagePioneersSTEMExp0K / 0.4 GB60
Mymodel0K / 0.1 GB50
C4ai Command R V01 SFT0K / 0.2 GB31
...inyllama Ft CodeAlpaca Adapter0K / 0.1 GB02
HH2 Temp0K / 3.6 GB201
...tai Prompts Falcon 15k V2 4bit0K / 0 GB31
Note: green Score (e.g. "73.2") means that the model is better than Dorjzodovsuren/Mongolian_Llama3-v0.1.