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

Apollo2 3.8B by FreedomIntelligence

 »  All LLMs  »  FreedomIntelligence  »  Apollo2 3.8B   URL Share it on

  27   
  Arxiv:2410.10626   Ar Base model:finetune:microsoft/... Base model:microsoft/phi-3-min...   Bg   Biology   Bm   Bs   Co   Cs   Custom code   Da Dataset:freedomintelligence/ap...   De   En   Eo   Es   Fr   Gd   Gl   Gn   Ha   He   Hi   Hr   Ig   Instruct   It   Ja   Ko   Ku   La   Lb   Ln   Lo   Medical   Mg   Mn   Mt   Phi3   Pt   Region:us   Ru   Rw   Sa   Safetensors   Sharded   Sk   Sq   Sr   Sw   Tensorflow   Th   Uk   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/FreedomIntelligence/Apollo2-3.8B 

Apollo2 3.8B Benchmarks

LLME Score: 0.21675
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Apollo2 3.8B (FreedomIntelligence/Apollo2-3.8B)

Apollo2 3.8B Parameters and Internals

Model Type 
question-answering
Additional Notes 
Democratizing Medical Large Language Models (LLMs) for multiple languages via a mixture of language family experts.
Supported Languages 
major_languages (ar, en, zh, ko, ja, de, pt, es, fr, ru, it, hi), minor_languages (mn, th, vi, lo, mg, hr, gl, cs, co, la, uk, bs, bg, eo, sq, da, sa, no, gn, sr, sk, gd, lb, ku, mt, he, ln, bm, sw, ig, rw, ha)
Release Notes 
Date:
2024.10.15
Notes:
ApolloMoE repo is published.
LLM NameApollo2 3.8B
Repository 🤗https://huggingface.co/FreedomIntelligence/Apollo2-3.8B 
Base Model(s)  Phi 3 Mini 4K Instruct   microsoft/Phi-3-mini-4k-instruct
Model Size3.8b
Required VRAM7.7 GB
Updated2025-03-24
MaintainerFreedomIntelligence
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesar en zh ko ja mn th vi lo mg de pt es fr ru it hr gl cs co la uk bs bg eo sq da sa gn sr sk gd lb hi ku mt he ln bm sw ig rw ha
Model ArchitecturePhi3ForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.42.3
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Apollo2 3.8B

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct128K / 7.7 GB268494385
Phi 3.5 Mini Instruct128K / 7.7 GB233354845
Phi 3 Mini 128K Instruct128K / 7.7 GB1799431636
Phi 4 Mini Instruct128K / 7.7 GB579411
NuExtract V1.5128K / 7.7 GB10851189
NuExtract 1.5128K / 7.7 GB13869222
...hi 4 Mini Instruct Abliterated128K / 7.7 GB4524
Flow Judge V0.1128K / 7.7 GB2254958
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB220
Glider128K / 15.4 GB155738
Note: green Score (e.g. "73.2") means that the model is better than FreedomIntelligence/Apollo2-3.8B.

Rank the Apollo2 3.8B 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? 45494 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