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

ReluFalcon 40B by SparseLLM

 »  All LLMs  »  SparseLLM  »  ReluFalcon 40B   URL Share it on

  49   
  Arxiv:2110.01786   Arxiv:2310.04564   Autotrain compatible   Custom code   En   Endpoints compatible   Falcon   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/SparseLLM/ReluFalcon-40B 

ReluFalcon 40B Benchmarks

LLME Score: 0.15099
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ReluFalcon 40B (SparseLLM/ReluFalcon-40B)

ReluFalcon 40B Parameters and Internals

Model Type 
Sparse Computation, Sparse Large Language Model, ReLU Activation
Use Cases 
Areas:
Research, Commercial applications
Limitations:
May produce inaccurate, biased or objectionable responses, Fine-tuning tested primarily in English, unknown results in other languages
Considerations:
Developers should perform safety testing and tuning before deploying applications of the model.
Additional Notes 
This is a fine-tuned version using ReLU activation to enhance sparse LLM efficiency.
Supported Languages 
English (tested)
Training Details 
Data Sources:
Wikipedia, Pile, StackOverflow
Data Volume:
5 billion tokens
Methodology:
Joint optimization on language modeling and knowledge distillation objectives. ReLU activation applied through fine-tuning techniques.
Hardware Used:
40x NVIDIA A100 GPUs with 80GB memory
Input Output 
Accepted Modalities:
text
LLM NameReluFalcon 40B
Repository 🤗https://huggingface.co/SparseLLM/ReluFalcon-40B 
Model Size40b
Required VRAM167.1 GB
Updated2025-02-05
MaintainerSparseLLM
Model Typefalcon
Model Files  9.2 GB: 1-of-18   9.8 GB: 2-of-18   9.2 GB: 3-of-18   9.8 GB: 4-of-18   9.2 GB: 5-of-18   9.8 GB: 6-of-18   9.2 GB: 7-of-18   9.8 GB: 8-of-18   9.2 GB: 9-of-18   9.8 GB: 10-of-18   9.2 GB: 11-of-18   9.8 GB: 12-of-18   9.2 GB: 13-of-18   9.8 GB: 14-of-18   9.2 GB: 15-of-18   9.8 GB: 16-of-18   9.2 GB: 17-of-18   5.9 GB: 18-of-18
Supported Languagesen
Model ArchitectureFalconForCausalLM
Licenseapache-2.0
Model Max Length1024
Transformers Version4.33.2
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size65024
Torch Data Typefloat32

Best Alternatives to ReluFalcon 40B

Best Alternatives
Context / RAM
Downloads
Likes
Tiny Random Falcon 40B2K / 0 GB1074590
Openbuddy Falcon 40B V16.1 4K2K / 82.6 GB13711
... Falcon 40B Instruct 4 Bit Bnb2K / 23.9 GB50
Falcon 40B0K / 83.6 GB1408192423
Falcon 40B Instruct0K / 83.6 GB1345261174
Tiny Random Falcon 40B0K / 0.2 GB8940
Falcon 40B Megacode20K / 82.5 GB151
...lcon 40B Ft Alpaca Dolly Dutch0K / 82.5 GB314
...slessMegaCoder Falcon 40B Mini0K / 82.5 GB12832
Falcon 40B Megacode2 Oasst0K / 82.5 GB186
Note: green Score (e.g. "73.2") means that the model is better than SparseLLM/ReluFalcon-40B.

Rank the ReluFalcon 40B 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? 42577 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