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

Falcon 180B Chat GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Falcon 180B Chat GPTQ   URL Share it on

  11   
  Arxiv:1911.02150   Arxiv:2005.14165   Arxiv:2104.09864   Arxiv:2205.14135   Arxiv:2306.01116   4-bit   4bit   Autotrain compatible Base model:quantized:tiiuae/fa... Base model:tiiuae/falcon-180b-... Dataset:tiiuae/falcon-refinedw...   De   En   Es   Falcon   Fr   Gptq   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Falcon-180B-Chat-GPTQ 

Falcon 180B Chat GPTQ Benchmarks

LLME Score: 0.11339
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Falcon 180B Chat GPTQ (TheBloke/Falcon-180B-Chat-GPTQ)
🌟 Advertise your project 🚀

Falcon 180B Chat GPTQ Parameters and Internals

Model Type 
falcon, causal decoder-only
Use Cases 
Areas:
chat, instruct model
Primary Use Cases:
Ready-to-use chat modeling based on Falcon-180B.
Limitations:
Mostly trained on English data, may not generalize to other languages., Out-of-scope for production use without risk assessment.
Considerations:
Develop appropriate precautions for any production use.
Additional Notes 
Model has multiquery attention and FlashAttention optimizations.
Supported Languages 
English (high proficiency), German (high proficiency), Spanish (high proficiency), French (high proficiency), Italian (limited proficiency), Portuguese (limited proficiency), Polish (limited proficiency), Dutch (limited proficiency), Romanian (limited proficiency), Czech (limited proficiency), Swedish (limited proficiency)
Training Details 
Data Sources:
Ultrachat, Platypus, Airoboros
Context Length:
2048
Hardware Used:
AWS SageMaker on up to 4,096 A100 40GB GPUs in P4d instances
Model Architecture:
Causal decoder-only model with positional embeddings rotary, multiquery attention, and parallel attention/MLP decoder-block with two layer norms.
Safety Evaluation 
Risk Categories:
Bias due to web content stereotypes
Ethical Considerations:
Carry stereotypes and biases commonly encountered online.
Responsible Ai Considerations 
Fairness:
Develop guardrails for production use to handle stereotypes and biases.
Input Output 
Input Format:
Prompts only
Accepted Modalities:
text
Output Format:
Generated text responses
Performance Tips:
Ensure using latest versions of recommended software and follow guidance for optimal hardware usage.
LLM NameFalcon 180B Chat GPTQ
Repository 🤗https://huggingface.co/TheBloke/Falcon-180B-Chat-GPTQ 
Model NameFalcon 180B Chat
Model CreatorTechnology Innovation Institute
Base Model(s)  tiiuae/falcon-180B-chat   tiiuae/falcon-180B-chat
Model Size180b
Required VRAM94.1 GB
Updated2025-08-20
MaintainerTheBloke
Model Typefalcon
Model Files  10.0 GB: 1-of-10   9.9 GB: 2-of-10   9.9 GB: 3-of-10   9.7 GB: 4-of-10   9.9 GB: 5-of-10   9.7 GB: 6-of-10   9.9 GB: 7-of-10   9.7 GB: 8-of-10   9.9 GB: 9-of-10   5.5 GB: 10-of-10
Supported Languagesen de es fr
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureFalconForCausalLM
Licenseunknown
Context Length2048
Model Max Length2048
Transformers Version4.33.0
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size65024
Torch Data Typefloat16

Best Alternatives to Falcon 180B Chat GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 180B GPTQ0K / 94.1 GB149
Largefalcon2K / 411.4 GB50
...buddy Falcon 180B V13 Preview02K / 358.1 GB17612
...buddy Falcon 180B V12 Preview02K / 358.1 GB17650
Airoboros 180B 2.2.12K / 154.2 GB160517
Airoboros 180B 2.2.1 AWQ2K / 96 GB96
...buddy Falcon 180B V13 Preview22K / 358.1 GB71
...buddy Falcon 180B V13 Preview12K / 358.1 GB104
Falcon 180B Chat AWQ2K / 96 GB88
...alcon 180B Omniquant W3a16g5122K / 69.4 GB53
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Falcon-180B-Chat-GPTQ.

Rank the Falcon 180B Chat GPTQ 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? 50767 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 v20241124
  Support LLM Explorer