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

SambaLingo Arabic Chat 70B by sambanovasystems

 »  All LLMs  »  sambanovasystems  »  SambaLingo Arabic Chat 70B   URL Share it on

  1890   
  Arxiv:2404.05829   Ar   Autotrain compatible   Conversational Dataset:huggingfaceh4/cai-conv... Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee...   En   Endpoints compatible   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sambanovasystems/SambaLingo-Arabic-Chat-70B 

SambaLingo Arabic Chat 70B Benchmarks

LLME Score: 0.20516
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SambaLingo Arabic Chat 70B (sambanovasystems/SambaLingo-Arabic-Chat-70B)

SambaLingo Arabic Chat 70B Parameters and Internals

Model Type 
Language Model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Language translation, Chatbots, Customer service
Primary Use Cases:
Arabic and English language chat models
Limitations:
Not for mission-critical applications, Not for applications involving the safety of others, Not for making highly important decisions
Considerations:
Please review license and out-of-scope use cases.
Additional Notes 
Model trained using preference optimization with multilingual datasets
Supported Languages 
Arabic (high), English (high)
Training Details 
Data Sources:
HuggingFaceH4/ultrachat_200k, HuggingFaceH4/ultrafeedback_binarized, HuggingFaceH4/cai-conversation-harmless, uonlp/CulturaX
Data Volume:
28 billion tokens from the Arabic split
Methodology:
Supervised fine-tuning (SFT) and Direct Performance Optimization (DPO)
Context Length:
2048
Input Output 
Input Format:
Chat template
Accepted Modalities:
text
Output Format:
Text generation
Performance Tips:
Set use_fast=False when loading the tokenizer
LLM NameSambaLingo Arabic Chat 70B
Repository 🤗https://huggingface.co/sambanovasystems/SambaLingo-Arabic-Chat-70B 
Model Size70b
Required VRAM39.9 GB
Updated2025-02-22
Maintainersambanovasystems
Model Typellama
Model Files  3.9 GB: 1-of-35   4.2 GB: 2-of-35   3.9 GB: 3-of-35   3.9 GB: 4-of-35   4.2 GB: 5-of-35   3.9 GB: 6-of-35   3.9 GB: 7-of-35   4.2 GB: 8-of-35   3.9 GB: 9-of-35   3.9 GB: 10-of-35   4.2 GB: 11-of-35   3.9 GB: 12-of-35   3.9 GB: 13-of-35   4.2 GB: 14-of-35   3.9 GB: 15-of-35   3.9 GB: 16-of-35   4.2 GB: 17-of-35   3.9 GB: 18-of-35   3.9 GB: 19-of-35   4.2 GB: 20-of-35   3.9 GB: 21-of-35   3.9 GB: 22-of-35   4.2 GB: 23-of-35   3.9 GB: 24-of-35   3.9 GB: 25-of-35   4.2 GB: 26-of-35   3.9 GB: 27-of-35   3.9 GB: 28-of-35   4.2 GB: 29-of-35   3.9 GB: 30-of-35   3.9 GB: 31-of-35   4.2 GB: 32-of-35   3.9 GB: 33-of-35   3.9 GB: 34-of-35   3.1 GB: 35-of-35   3.9 GB: 1-of-35   4.2 GB: 2-of-35   3.9 GB: 3-of-35   3.9 GB: 4-of-35   4.2 GB: 5-of-35   3.9 GB: 6-of-35   3.9 GB: 7-of-35   4.2 GB: 8-of-35   3.9 GB: 9-of-35   3.9 GB: 10-of-35
Supported Languagesar en
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Vocabulary Size57344
Torch Data Typefloat32

Best Alternatives to SambaLingo Arabic Chat 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB25245
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB199121
Llama3 Function Calling 1048K1024K / 141.9 GB61
...a 3 70B Instruct Gradient 524K512K / 141.9 GB23323
...a 3 70B Instruct Gradient 262K256K / 141.9 GB18655
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB3212
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB653
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB120
Yi 70B 200K RPMerge Franken195K / 142.4 GB101
Note: green Score (e.g. "73.2") means that the model is better than sambanovasystems/SambaLingo-Arabic-Chat-70B.

Rank the SambaLingo Arabic Chat 70B 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