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

Llama 65B Int4 by Agtian

 »  All LLMs  »  Agtian  »  Llama 65B Int4   URL Share it on

  17   
  Autotrain compatible   Endpoints compatible   Llama   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/Agtian/llama-65b-int4 

Llama 65B Int4 Benchmarks

LLME Score: 0.07437
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 65B Int4 (Agtian/llama-65b-int4)
🌟 Advertise your project 🚀

Llama 65B Int4 Parameters and Internals

Model Type 
auto-regressive language model, transformer architecture
Use Cases 
Areas:
research on large language models
Primary Use Cases:
question answering, natural language understanding, reading comprehension
Limitations:
generation of misinformation, generation of harmful, biased or offensive content
Considerations:
Should not be used on downstream applications without further investigation and mitigations of risks.
Additional Notes 
Model date: Trained between December 2022 and February 2023. Model version: 1.
Supported Languages 
bg (unknown), ca (unknown), cs (unknown), da (unknown), de (unknown), en (better performance expected), es (unknown), fr (unknown), hr (unknown), hu (unknown), it (unknown), nl (unknown), pl (unknown), pt (unknown), ro (unknown), ru (unknown), sl (unknown), sr (unknown), sv (unknown), uk (unknown)
Training Details 
Data Sources:
CCNet, C4, GitHub, Wikipedia, Books, ArXiv, Stack Exchange
Safety Evaluation 
Risk Categories:
misinformation, bias
Ethical Considerations:
Data contains offensive, harmful, and biased content. Evaluated on RAI datasets for biases.
Responsible Ai Considerations 
Fairness:
Evaluated on RAI datasets for biases in gender, religion, race, sexual orientation, age, nationality, disability, physical appearance, and socio-economic status.
Transparency:
Results on evaluation datasets and ethical considerations are mentioned.
Mitigation Strategies:
Data filtered based on proximity to Wikipedia text and references using a Kneser-Ney language model and a fastText linear classifier.
LLM NameLlama 65B Int4
Repository 🤗https://huggingface.co/Agtian/llama-65b-int4 
Model Size65b
Required VRAM33.5 GB
Updated2025-06-17
MaintainerAgtian
Model Typellama
Model Files  33.5 GB
Model ArchitectureLLaMAForCausalLM
Licenseother
Transformers Version4.27.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Llama 65B Int4

Model
Likes
Downloads
VRAM
Llama 65B 4bit61033 GB

Best Alternatives to Llama 65B Int4

Best Alternatives
Context / RAM
Downloads
Likes
Llama 65B Hf0K / 72 GB8123
Llama 65B Hf0K / 75.2 GB60
Llama 65B0K / 72 GB210
LLaMA 65B HF0K / 73.6 GB1119
Deepshard 65B Raw0K / 73.6 GB61
Llama 65B 4bit0K / 33.5 GB106
Note: green Score (e.g. "73.2") means that the model is better than Agtian/llama-65b-int4.

Rank the Llama 65B Int4 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? 51368 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