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

Swahili Gemma by Mollel

 »  All LLMs  »  Mollel  »  Swahili Gemma   URL Share it on

  43   
  4bit   Autotrain compatible   Conversational   En   Endpoints compatible   Gemma   Pytorch   Quantized   Region:us   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Mollel/Swahili_Gemma 

Swahili Gemma Benchmarks

ARC: 58.96 vs 96.7 (so35)-39%
HellaSwag: 76.4 vs 95.3 (gpt4)-19.8%
MMLU: 61.02 vs 88.3 (so35)-30.9%
TruthfulQA: 52.1 vs 59 (gpt4)-11.7%
WinoGrande: 75.61 vs 87.5 (gpt4)-13.6%
GSM8K: 43.82 vs 96.4 (so35)-54.5%
LLME Score: 0.20837
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Swahili Gemma (Mollel/Swahili_Gemma)

Swahili Gemma Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, gemma, trl
LLM NameSwahili Gemma
Repository 🤗https://huggingface.co/Mollel/Swahili_Gemma 
Base Model(s)  gemma-7b-bnb-4bit   /gemma-7b-bnb-4bit
Model Size7b
Required VRAM17.1 GB
Updated2024-12-22
MaintainerMollel
Model Typegemma
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
Supported Languagesen
Quantization Type4bit
Model ArchitectureGemmaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Quantized Models of the Swahili Gemma

Model
Likes
Downloads
VRAM
DAD Model Gemma V30115 GB

Best Alternatives to Swahili Gemma

Best Alternatives
Context / RAM
Downloads
Likes
...t Cleaner Gemma 32k Merged 16b31K / 17.1 GB170
...ruct Malayalam Model Vllm 4bit16K / 5.6 GB170
... Codegemma 2 7B It Alpaca V1.28K / 17.1 GB200
Codegemma 7B It 8bit8K / 9.5 GB3444
Gemma 7B Bnb 4bit8K / 5.6 GB394117
Fbt Gemma 7B8K / 17.1 GB120
Codegemma 7B It 4bit8K / 5.9 GB431
Codegemma 7B 4bit8K / 5.9 GB220
Gemma 1.1 7B It 4bit8K / 5.9 GB154
Gemma 1.1 7B It 4bit8K / 5.9 GB161
Note: green Score (e.g. "73.2") means that the model is better than Mollel/Swahili_Gemma.

Rank the Swahili Gemma 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? 40066 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 v20241217
  Support LLM Explorer