MiniMA 2 3B GGUF by andrijdavid

 ยป  All LLMs  ยป  andrijdavid  ยป  MiniMA 2 3B GGUF   URL Share it on

  Arxiv:2311.07052   Autotrain compatible   Dataset:eleutherai/pile   Dataset:p208p2002/wudao Dataset:togethercomputer/redpa...   En   Endpoints compatible   Gguf   Llama   Q2   Quantized   Region:us   Zh

MiniMA 2 3B GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MiniMA 2 3B GGUF (andrijdavid/MiniMA-2-3B-GGUF)

MiniMA 2 3B GGUF Parameters and Internals

Model Type 
language model
Additional Notes 
Continuation from MiniMA-3B with better data mixture and more trained tokens.
Supported Languages 
en (English), zh (Chinese)
LLM NameMiniMA 2 3B GGUF
Repository ๐Ÿค—https://huggingface.co/andrijdavid/MiniMA-2-3B-GGUF 
Model Size3b
Required VRAM1.3 GB
Updated2025-02-05
Maintainerandrijdavid
Model Typellama
Model Files  1.3 GB   1.5 GB   1.6 GB   1.5 GB   1.4 GB   1.7 GB   1.9 GB   1.9 GB   1.9 GB   1.8 GB   2.1 GB   2.3 GB   2.1 GB   2.1 GB   2.1 GB   2.5 GB   3.2 GB   6.0 GB
Supported Languagesen zh
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.33.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size49216
Torch Data Typefloat16

Best Alternatives to MiniMA 2 3B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 MEDIT 3B O1128K / 6.5 GB83412
Gunny128K / 6.5 GB1540
ReWiz Llama 3.2 3B128K / 6.5 GB2222
HelpingAI 3B Reloaded128K / 5.7 GB2081
HelpingAI2 3B128K / 5.7 GB6791
Llama 3.2 3B COT128K / 6.5 GB1621
Llm 3 2 Flux Prompt128K / 6.5 GB3507
3BigReasonCinder4K / 6.1 GB1200
Vizuosense Gguf2K / 2.1 GB170
...2 3B Instruct Unsloth Bnb 4bit128K / 2.4 GB282153
Note: green Score (e.g. "73.2") means that the model is better than andrijdavid/MiniMA-2-3B-GGUF.

Rank the MiniMA 2 3B GGUF Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227