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

SambaLingo Thai Chat by sambanovasystems

 »  All LLMs  »  sambanovasystems  »  SambaLingo Thai Chat   URL Share it on

  132   
  Arxiv:2404.05829   Autotrain compatible   Conversational Dataset:huggingfaceh4/cai-conv... Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee...   En   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/sambanovasystems/SambaLingo-Thai-Chat 

SambaLingo Thai Chat Benchmarks

ARC: 52.73 vs 96.7 (so35)-45.5%
HellaSwag: 78.42 vs 95.3 (gpt4)-17.7%
MMLU: 43.95 vs 88.3 (so35)-50.2%
TruthfulQA: 40.84 vs 59 (gpt4)-30.8%
WinoGrande: 72.22 vs 87.5 (gpt4)-17.5%
GSM8K: 8.57 vs 96.4 (so35)-91.1%
LLME Score: 0.1726
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SambaLingo Thai Chat (sambanovasystems/SambaLingo-Thai-Chat)
🌟 Advertise your project 🚀

SambaLingo Thai Chat Parameters and Internals

Model Type 
Language Model
Use Cases 
Areas:
research, commercial applications
Limitations:
Mission-critical applications, Safety applications, Important decision making
Additional Notes 
Extended vocabulary to 57,000 tokens from the original llama model.
Supported Languages 
Thai (Advanced), English (Advanced)
Training Details 
Data Sources:
HuggingFaceH4/ultrachat_200k, HuggingFaceH4/ultrafeedback_binarized, HuggingFaceH4/cai-conversation-harmless
Data Volume:
38 billion tokens from the Thai split
Methodology:
SFT and Direct Performance Optimization
Context Length:
2048
Model Architecture:
LLama-2-Adaptation
Input Output 
Input Format:
<|user|>\n{question}~~\n<|assistant|>\n
Accepted Modalities:
text
Output Format:
Generated text in response to provided prompt
LLM NameSambaLingo Thai Chat
Repository 🤗https://huggingface.co/sambanovasystems/SambaLingo-Thai-Chat 
Model Size6.9b
Required VRAM13.9 GB
Updated2025-09-23
Maintainersambanovasystems
Model Typellama
Model Files  5.0 GB: 1-of-3   4.9 GB: 2-of-3   4.0 GB: 3-of-3
Supported Languagesth en
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size57344
Torch Data Typebfloat16

Best Alternatives to SambaLingo Thai Chat

Best Alternatives
Context / RAM
Downloads
Likes
Bolna Lead Qualification16K / 13.8 GB43
STP Model Lean 03204K / 13.8 GB29250
Sambanova Llama2 1004K / 13.9 GB50
Gorilla Finetuned4K / 13.8 GB60
Deep Neural V14K / 27.7 GB650
...j Pair8 Ds Coder Rmsprop Iter44K / 13.9 GB1450
... Ds Coder Reflct Rmsprop Iter44K / 13.9 GB1050
...8 Ds Chat Reflct Rmsprop Iter24K / 13.9 GB870
... Ds Coder Reflct Rmsprop Iter34K / 13.9 GB700
...4 Ds Chat Reflct Rmsprop Iter34K / 13.9 GB1100
Note: green Score (e.g. "73.2") means that the model is better than sambanovasystems/SambaLingo-Thai-Chat.

Rank the SambaLingo Thai Chat 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? 51540 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