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

Openbuddy Llama3.1 8B Bnb 4bit by A2va

 »  All LLMs  »  A2va  »  Openbuddy Llama3.1 8B Bnb 4bit   URL Share it on

  19   
  4-bit   4bit   Autotrain compatible Base model:openbuddy/openbuddy... Base model:quantized:openbuddy...   Bitsandbytes   Conversational   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/A2va/openbuddy-llama3.1-8b-bnb-4bit 

Openbuddy Llama3.1 8B Bnb 4bit Benchmarks

LLME Score: 0.22765
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openbuddy Llama3.1 8B Bnb 4bit (A2va/openbuddy-llama3.1-8b-bnb-4bit)

Openbuddy Llama3.1 8B Bnb 4bit Parameters and Internals

Model Type 
Multilingual Chatbot
Use Cases 
Areas:
English and Chinese Multilingual Applications
Applications:
Chatbot Services
Primary Use Cases:
Provides helpful and logical assistance
Limitations:
Inherent limitations include the potential for erroneous, offensive, or undesirable outputs. Not suitable for critical or high-stakes scenarios.
Considerations:
Do not use in situations leading to personal injury, property damage, or significant losses.
Additional Notes 
Quantized in the unsloth way.
Supported Languages 
English (proficient), Chinese (proficient)
Training Details 
Data Sources:
Meta Llama 3
Methodology:
Quantized in the unsloth way
Responsible Ai Considerations 
Fairness:
Ensure responses are socially unbiased and positive in nature.
Accountability:
OpenBuddy team from https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy
Mitigation Strategies:
OpenBuddy cannot access the internet and is designed to avoid harmful content.
Input Output 
Input Format:
<|role|><role type><|says|><content><|end|>
Accepted Modalities:
text
Output Format:
Textual conversational outputs
Performance Tips:
Use the fast tokenizer from `transformers`.
LLM NameOpenbuddy Llama3.1 8B Bnb 4bit
Repository 🤗https://huggingface.co/A2va/openbuddy-llama3.1-8b-bnb-4bit 
Base Model(s)  OpenBuddy/openbuddy-llama3.1-8b-v22.3-131k   OpenBuddy/openbuddy-llama3.1-8b-v22.3-131k
Model Size8b
Required VRAM5.8 GB
Updated2024-12-22
MaintainerA2va
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad0|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Openbuddy Llama3.1 8B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB152
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB121
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB82
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1425
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB3417
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB143
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB91
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB141
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB91

Rank the Openbuddy Llama3.1 8B Bnb 4bit 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? 40066 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