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

Mixtral AI SwahiliTron 7B by LeroyDyer

 »  All LLMs  »  LeroyDyer  »  Mixtral AI SwahiliTron 7B   URL Share it on

  21   

Mixtral AI SwahiliTron 7B is an open-source language model by LeroyDyer. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: mit, HF Score: 61.1, LLM Explorer Score: 0.17, Arc: 57.1, HellaSwag: 81.6, MMLU: 58.5, TruthfulQA: 60.7, WinoGrande: 75.5, GSM8K: 33.5.

  Autotrain compatible Dataset:rogendo/english-swahil...   Dataset:uonlp/culturax   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Sw   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LeroyDyer/Mixtral_AI_SwahiliTron_7b 

Mixtral AI SwahiliTron 7b Benchmarks

MMLU Pro: 2.31
GPQA: 2.01
MUSR: 1.92
BBH: 3.21
IFEval: 15.34 vs 88 (so35)-82.6%
ARC: 57.08 vs 96.7 (so35)-41%
HellaSwag: 81.59 vs 95.3 (gpt4)-14.4%
MMLU: 58.49 vs 88.3 (so35)-33.8%
TruthfulQA: 60.66 vs 59 (gpt4)2.8%
WinoGrande: 75.53 vs 87.5 (gpt4)-13.7%
GSM8K: 33.51 vs 96.4 (so35)-65.2%
MATH Lvl 5: 1.36
LLME Score: 0.16704
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral AI SwahiliTron 7B (LeroyDyer/Mixtral_AI_SwahiliTron_7b)
🌟 Advertise your project 🚀

Mixtral AI SwahiliTron 7B Parameters and Internals

Additional Notes 
This model is updated for RAG tasks in Swahili or English and undergoes fine-tuning stages, including merging and retuning stages. It is designed to apply LoRA adapters from the hub and can be set to train mode: model.train()
Supported Languages 
en (primary), sw (primary)
Training Details 
Data Sources:
uonlp/CulturaX, Rogendo/English-Swahili-Sentence-Pairs
Methodology:
RAG, tasks in Swahili or English, programming, school works, bible, and sacred historical texts
LLM NameMixtral AI SwahiliTron 7b
Repository 🤗https://huggingface.co/LeroyDyer/Mixtral_AI_SwahiliTron_7b 
Model Size7b
Required VRAM14.4 GB
Updated2024-08-30
MaintainerLeroyDyer
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen sw
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mixtral AI SwahiliTron 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
MegaBeam Mistral 7B 512K512K / 14.4 GB890850
SpydazWeb AI HumanAI RP512K / 14.4 GB141
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB808216
Hebrew Mistral 7B 200K256K / 30 GB131615
Astral 256K 7B V2250K / 14.4 GB50
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than LeroyDyer/Mixtral_AI_SwahiliTron_7b.

Rank the Mixtral AI SwahiliTron 7B 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? 51648 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b
  Support LLM Explorer