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

SeaLLM 7B V2.5 AWQ by NghiemAbe

 »  All LLMs  »  NghiemAbe  »  SeaLLM 7B V2.5 AWQ   URL Share it on

  5   
  Arxiv:2306.05179   Arxiv:2312.00738   4-bit   Autotrain compatible   Awq   Conversational   En   Endpoints compatible   Gemma   Id   Km   Lo   Ms   Multilingual   My   Quantized   Region:us   Safetensors   Sea   Sharded   Tensorflow   Th   Tl   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/NghiemAbe/SeaLLM-7B-v2.5-AWQ 

SeaLLM 7B V2.5 AWQ Benchmarks

ARC: 63.48 vs 96.7 (so35)-34.4%
HellaSwag: 81.54 vs 95.3 (gpt4)-14.4%
MMLU: 64.93 vs 88.3 (so35)-26.5%
TruthfulQA: 53.78 vs 59 (gpt4)-8.8%
WinoGrande: 76.32 vs 87.5 (gpt4)-12.8%
GSM8K: 74.37 vs 96.4 (so35)-22.9%
LLME Score: 0.2112
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 🚀

SeaLLM 7B V2.5 AWQ Parameters and Internals

LLM NameSeaLLM 7B V2.5 AWQ
Repository 🤗https://huggingface.co/NghiemAbe/SeaLLM-7B-v2.5-AWQ 
Base Model(s)  SeaLLMs/SeaLLM-7B-v2.5   SeaLLMs/SeaLLM-7B-v2.5
Model Size7b
Required VRAM5.6 GB
Updated2024-12-03
MaintainerNghiemAbe
Model Typegemma
Model Files  5.0 GB: 1-of-2   0.6 GB: 2-of-2
Supported Languagesen zh vi id th ms km lo my tl
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureGemmaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16
SeaLLM 7B V2.5 AWQ (NghiemAbe/SeaLLM-7B-v2.5-AWQ)

Best Alternatives to SeaLLM 7B V2.5 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Codegemma 7B AWQ8K / 7.2 GB90
SeaLLM 7B V2.5 AWQ8K / 7.2 GB2052
Gemma 1.1 7B It AWQ8K / 7.2 GB80
CodeGemma 7B AWQ8K / 7.2 GB80
Gemma Ko 7B AWQ8K / 5.6 GB100
Codegemma 1.1 7B It AWQ8K / 7.2 GB100
Gemma 7B It AWQ8K / 7.2 GB502
Gemma 7B AWQ8K / 7.2 GB140
Gemma 7B It AWQ8K / 7.2 GB50
...t Cleaner Gemma 32k Merged 16b31K / 17.1 GB110
Note: green Score (e.g. "73.2") means that the model is better than NghiemAbe/SeaLLM-7B-v2.5-AWQ.

Rank the SeaLLM 7B V2.5 AWQ 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? 38770 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