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

Sea Lion 7B Instruct Gptq by aisingapore

 »  All LLMs  »  aisingapore  »  Sea Lion 7B Instruct Gptq   URL Share it on

  5   
  4bit   Autotrain compatible   Custom code   En   Gptq   Id   Instruct   Km   Lo   Mpt   Ms   My   Quantized   Region:us   Ta   Th   Tl   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/aisingapore/sea-lion-7b-instruct-gptq 

Sea Lion 7B Instruct Gptq Benchmarks

LLME Score: 0.15694
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Sea Lion 7B Instruct Gptq Parameters and Internals

Model Type 
Decoder
Additional Notes 
SEA-LION is aimed at supporting Southeast Asian languages with open and high-quality datasets.
Supported Languages 
en (high), zh (high), id (high), vi (high), ms (high), tl (high), ta (high), my (high), th (high), lo (high), km (high)
Training Details 
Data Sources:
Commercially permissive datasets
Methodology:
Parameter efficient fine tuning using LoRA
Hardware Used:
8x A100-40GB
Input Output 
Input Format:
Tokenized text
Accepted Modalities:
text
Output Format:
Text completions
Performance Tips:
Adjust generation parameters like temperature and top_k for different results.
LLM NameSea Lion 7B Instruct Gptq
Repository 🤗https://huggingface.co/aisingapore/sea-lion-7b-instruct-gptq 
Base Model(s)  Sea Lion 7B Instruct   aisingapore/sea-lion-7b-instruct
Model Size7b
Required VRAM5.5 GB
Updated2025-04-02
Maintaineraisingapore
Model Typempt
Instruction-BasedYes
Model Files  5.5 GB
Supported Languagesen zh id vi ms tl my th lo km ta
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureMPTForCausalLM
Licensemit
Transformers Version4.38.2
Tokenizer ClassSEABPETokenizer
Padding Token<|padding|>
Vocabulary Size256000
Torch Data Typefloat16
Sea Lion 7B Instruct Gptq (aisingapore/sea-lion-7b-instruct-gptq)

Best Alternatives to Sea Lion 7B Instruct Gptq

Best Alternatives
Context / RAM
Downloads
Likes
SEA LION V1 7B IT GPTQ0K / 5.5 GB300
SEA LION V1 7B IT GBTQ0K / 5.5 GB70
Mpt 7B 8K Chat Gptq0K / 3.8 GB642
Mpt 7B Chat Q80K / 6.9 GB481
Mpt 7B Instruct Q80K / 6.9 GB192
Mpt 7B Chat0K / 13.3 GB84759514
Mpt 7B Instruct0K / 13.3 GB8660470
Mpt 7B Int8 Ov0K / 0 GB210
Sea Lion 7B Instruct0K / 15 GB20823
Mpt 7B 8K Instruct0K / 13.3 GB72526
Note: green Score (e.g. "73.2") means that the model is better than aisingapore/sea-lion-7b-instruct-gptq.

Rank the Sea Lion 7B Instruct 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? 48075 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