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

MicroLlama by keeeeenw

 »  All LLMs  »  keeeeenw  »  MicroLlama   URL Share it on

  1732   
  Arxiv:2401.02385   Autotrain compatible Dataset:cerebras/slimpajama-62...   En   Endpoints compatible   Llama   Model-index   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/keeeeenw/MicroLlama 

MicroLlama Benchmarks

MMLU Pro: 1.53
GPQA: 1.45
MUSR: 4.79
BBH: 2.83
IFEval: 19.85 vs 88 (so35)-77.4%
MATH Lvl 5: 1.13
LLME Score: 0.20054
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

MicroLlama Parameters and Internals

Model Type 
text-generation
Additional Notes 
Project evolved from TinyLlama; a smaller model setup was developed to fit budget and resource constraints.
Supported Languages 
en (NLP)
Training Details 
Data Sources:
cerebras/SlimPajama-627B
Data Volume:
50B tokens
Context Length:
2048
Hardware Used:
4 x Nvidia 4090
Model Architecture:
block_size=2048, vocab_size=32000, padding_multiple=64, n_layer=12, n_head=16, n_embd=1024, rotary_percentage=1.0, parallel_residual=False, bias=False, _norm_class="FusedRMSNorm", norm_eps=1e-5, _mlp_class="LLaMAMLP", intermediate_size=5632, n_query_groups=4
LLM NameMicroLlama
Repository 🤗https://huggingface.co/keeeeenw/MicroLlama 
Model Size627b
Required VRAM1.2 GB
Updated2025-06-09
Maintainerkeeeeenw
Model Typellama
Model Files  1.2 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.39.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat32
MicroLlama (keeeeenw/MicroLlama)

Quantized Models of the MicroLlama

Model
Likes
Downloads
VRAM
...llama Python Instruct 0.3 4bit0300 GB

Best Alternatives to MicroLlama

Best Alternatives
Context / RAM
Downloads
Likes
TinyLlama V1.12K / 4.4 GB13800997
CroissantLLMBase2K / 5.4 GB111032
TinyLlama V1.1 Math Code2K / 4.4 GB374611
TinyLlama V1.1 Chinese2K / 4.4 GB151010
...Llama 1.1B 1.5T OpenOrca Alpha2K / 2.2 GB264
TinyLlama 1.1B 1T OpenOrca2K / 2.2 GB147
...inyLlama 1.1B 1T OpenOrca GPTQ2K / 0.8 GB412
TinyLlama 1.1B 1T OpenOrca AWQ2K / 0.8 GB132
Note: green Score (e.g. "73.2") means that the model is better than keeeeenw/MicroLlama.

Rank the MicroLlama 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? 48023 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 v20241124
  Support LLM Explorer