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

Llama3 Aloe 8B Alpha by HPAI-BSC

 »  All LLMs  »  HPAI-BSC  »  Llama3 Aloe 8B Alpha   URL Share it on

  21528   
  Arxiv:2405.01886   Autotrain compatible   Biology   Dataset:argilla/dpo-mix-7k   Dataset:bigbio/med qa   Dataset:bigbio/pubmed qa Dataset:gbaker/medqa-usmle-4-o...   Dataset:hkust-nlp/deita-10k-v0 Dataset:hpai-bsc/better-safe-t...   Dataset:hpai-bsc/careqa   Dataset:hpai-bsc/medmcqa-cot   Dataset:hpai-bsc/medqa-cot   Dataset:hpai-bsc/pubmedqa-cot Dataset:jondurbin/airoboros-3....   Dataset:ldjnr/capybara   Dataset:lukaemon/mmlu   Dataset:nvidia/helpsteer Dataset:openlifescienceai/medm...   En   Endpoints compatible   Instruct   Llama   Medical   Pytorch   Region:us   Safetensors   Sharded
Model Card on HF 🤗: https://huggingface.co/HPAI-BSC/Llama3-Aloe-8B-Alpha 

Llama3 Aloe 8B Alpha Benchmarks

MMLU Pro: 25.5
GPQA: 5.93
MUSR: 5.88
BBH: 27.15
IFEval: 50.81 vs 88 (so35)-42.3%
MATH Lvl 5: 5.36
LLME Score: 0.32765
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 Aloe 8B Alpha (HPAI-BSC/Llama3-Aloe-8B-Alpha)

Llama3 Aloe 8B Alpha Parameters and Internals

Model Type 
Causal decoder-only transformer language model
Use Cases 
Areas:
research
Applications:
building foundational models for healthcare
Primary Use Cases:
research purposes, stepping stone for foundational models
Limitations:
not for clinical practice, not for medical diagnosis, not for direct or indirect healthcare advice, prone to error, can produce toxic content
Supported Languages 
English (mainly)
Training Details 
Data Sources:
argilla/dpo-mix-7k, nvidia/HelpSteer, jondurbin/airoboros-3.2, hkust-nlp/deita-10k-v0, LDJnr/Capybara, HPAI-BSC/CareQA, GBaker/MedQA-USMLE-4-options, lukaemon/mmlu, bigbio/pubmed_qa, openlifescienceai/medmcqa, bigbio/med_qa, HPAI-BSC/better-safe-than-sorry, HPAI-BSC/pubmedqa-cot, HPAI-BSC/medmcqa-cot, HPAI-BSC/medqa-cot
Methodology:
Supervised fine-tuning on top of Llama 3 8B using medical and general domain datasets, model merging using DARE-TIES process, two-stage DPO process for human preference alignment
LLM NameLlama3 Aloe 8B Alpha
Repository 🤗https://huggingface.co/HPAI-BSC/Llama3-Aloe-8B-Alpha 
Model Size8b
Required VRAM16.1 GB
Updated2024-12-22
MaintainerHPAI-BSC
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3 Aloe 8B Alpha

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB4850678
MrRoboto ProLong 8B V4i1024K / 16.1 GB461
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
MrRoboto ProLong 8B V2b1024K / 16.1 GB1770
MrRoboto ProLong 8B V1n1024K / 16.1 GB1760
MrRoboto ProLong 8B V4b1024K / 16.1 GB1040
...o ProLongBASE Pt6 Unaligned 8B1024K / 16.1 GB600
MrRoboto ProLong 8B V4c1024K / 16.1 GB850
HEL V0.8 8B LONG DARK1024K / 16.1 GB2000
MrRoboto ProLong 8B V1a1024K / 16.1 GB1080
Note: green Score (e.g. "73.2") means that the model is better than HPAI-BSC/Llama3-Aloe-8B-Alpha.

Rank the Llama3 Aloe 8B Alpha 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? 40123 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