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

Mistral Nemo Kurdish by nazimali

 »  All LLMs  »  nazimali  »  Mistral Nemo Kurdish   URL Share it on

  102   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-n...   Conversational Dataset:nazimali/kurdish-wikip...   En   Endpoints compatible   Instruct   Ku   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/nazimali/Mistral-Nemo-Kurdish 

Mistral Nemo Kurdish Benchmarks

MMLU Pro: 24.83
GPQA: 6.82
MUSR: 11.78
BBH: 29.86
IFEval: 34.01 vs 88 (so35)-61.4%
MATH Lvl 5: 9.59
LLME Score: 0.2822
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Nemo Kurdish (nazimali/Mistral-Nemo-Kurdish)

Mistral Nemo Kurdish Parameters and Internals

Model Type 
text-generation-inference
Use Cases 
Primary Use Cases:
Should be fine-tuned further for a specific task.
Considerations:
See instruction fine-tuned model [nazimali/Mistral-Nemo-Kurdish-Instruct](https://huggingface.co/nazimali/Mistral-Nemo-Kurdish-Instruct).
Additional Notes 
Model should be further fine-tuned to improve its performance in Kurdish.
Supported Languages 
ku (Kurdish (Kurmanji and Sorani)), en (English)
Training Details 
Data Sources:
nazimali/kurdish-wikipedia-articles
Data Volume:
62,720 (out of 63,076)
Methodology:
Continued pre-training with 'unsloth' and quantization using 'bitsandbytes'.
Training Time:
6h 31m 4s
Hardware Used:
1 NVIDIA A100 80GB PCIe
Input Output 
Input Format:
Gotara Wikipedia ### Sernav: {} ### Gotar: {}
Accepted Modalities:
text
LLM NameMistral Nemo Kurdish
Repository 🤗https://huggingface.co/nazimali/Mistral-Nemo-Kurdish 
Base Model(s)  Mistral Nemo Instruct 2407   mistralai/Mistral-Nemo-Instruct-2407
Model Size12.2b
Required VRAM24.5 GB
Updated2025-02-22
Maintainernazimali
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesku en
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Quantized Models of the Mistral Nemo Kurdish

Model
Likes
Downloads
VRAM
Mistral Nemo Kurdish Instruct216124 GB

Best Alternatives to Mistral Nemo Kurdish

Best Alternatives
Context / RAM
Downloads
Likes
Violet Twilight V0.21000K / 24.5 GB53638729
...ish Mistral Nemo Instruct 24071000K / 24.5 GB772
Educa Ai Nemo Sft1000K / 49.3 GB5434
Crimson Dawn V0.21000K / 24.5 GB9713
...al Nemo Japanese Instruct 24081000K / 24.5 GB338434
Azure Dusk V0.21000K / 24.5 GB667
...ike Mistral Nemo Instruct 24071000K / 24.5 GB23210
...l Nemo Abliterated Nemo Pro V21000K / 24.5 GB260
ChatML Nemo Pro1000K / 24.5 GB112
MN SlushoMix1000K / 24.5 GB192
Note: green Score (e.g. "73.2") means that the model is better than nazimali/Mistral-Nemo-Kurdish.

Rank the Mistral Nemo Kurdish 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? 43470 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