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 Ov Int8 by fakezeta

 »  All LLMs  »  fakezeta  »  Llama3 Aloe 8B Alpha Ov Int8   URL Share it on

  38   
  Arxiv:2405.01886   Autotrain compatible   Biology   Conversational   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:jondurbin/airoboros-3....   Dataset:ldjnr/capybara   Dataset:lukaemon/mmlu   Dataset:nvidia/helpsteer Dataset:openlifescienceai/medm...   En   Endpoints compatible   Llama   Medical   Openvino   Region:us
Model Card on HF 🤗: https://huggingface.co/fakezeta/Llama3-Aloe-8B-Alpha-ov-int8 

Llama3 Aloe 8B Alpha Ov Int8 Benchmarks

LLME Score: 0.18625
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 Ov Int8 (fakezeta/Llama3-Aloe-8B-Alpha-ov-int8)

Llama3 Aloe 8B Alpha Ov Int8 Parameters and Internals

Model Type 
Causal decoder-only transformer
Use Cases 
Areas:
Research
Primary Use Cases:
As a stepping stone to build better foundational models for healthcare
Limitations:
Not to be used for clinical practice, medical diagnosis, or any other form of direct or indirect healthcare advice., Activities harmful for individuals, such as spam, fraud, or impersonation, are prohibited.
Additional Notes 
Aloe has been tested on popular healthcare QA datasets, with a new family of healthcare LLMs that reaches state-of-the-art results at its size, using model merging and advanced prompting strategies.
Supported Languages 
English (mainly)
Training Details 
Data Sources:
Medical domain datasets, including synthetic data generated using Mixtral-8x7B and Genstruct, LDJnr/Capybara, hkust-nlp/deita-10k-v0, jondurbin/airoboros-3.2, argilla/dpo-mix-7k, nvidia/HelpSteer
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
Context Length:
8192
Hardware Used:
4xH100
Safety Evaluation 
Risk Categories:
Healthcare professional impersonation, Medical decision-making without professional supervision, Access to information on dangerous substances or procedures
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Medprompting provides a 7% increase in reported accuracy.
LLM NameLlama3 Aloe 8B Alpha Ov Int8
Repository 🤗https://huggingface.co/fakezeta/Llama3-Aloe-8B-Alpha-ov-int8 
Model Size8b
Required VRAM8 GB
Updated2025-02-22
Maintainerfakezeta
Model Typellama
Model Files  8.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256

Best Alternatives to Llama3 Aloe 8B Alpha Ov Int8

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB3927680
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
MrRoboto BASE V2 Unholy 8B 64K1024K / 16.1 GB271
Mpasila Viking 8B1024K / 16.1 GB840
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
41024K / 16.1 GB3220
Hel V2 8B DARK FICTION1024K / 16.1 GB220
161024K / 16.1 GB1690
...di95 LewdStorytellerMix 8B 64K1024K / 16.1 GB692
Note: green Score (e.g. "73.2") means that the model is better than fakezeta/Llama3-Aloe-8B-Alpha-ov-int8.

Rank the Llama3 Aloe 8B Alpha Ov Int8 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? 43470 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