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

Typhoon 7B by scb10x

 »  All LLMs  »  scb10x  »  Typhoon 7B   URL Share it on

  1163   
  Arxiv:2312.13951   Autotrain compatible   Endpoints compatible   Mistral   Pretrained   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/scb10x/typhoon-7b 

Typhoon 7B Benchmarks

ARC: 58.53 vs 96.7 (so35)-39.5%
HellaSwag: 81.55 vs 95.3 (gpt4)-14.4%
MMLU: 59.54 vs 88.3 (so35)-32.6%
TruthfulQA: 40.52 vs 59 (gpt4)-31.3%
WinoGrande: 76.56 vs 87.5 (gpt4)-12.5%
GSM8K: 31.61 vs 96.4 (so35)-67.2%
LLME Score: 0.21761
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Typhoon 7B (scb10x/typhoon-7b)

Typhoon 7B Parameters and Internals

Model Type 
pretrained, decoder-only, text-generation
Use Cases 
Limitations:
May not follow human instructions without one/few-shot learning or instruction fine-tuning, Does not have moderation mechanisms and may generate harmful or inappropriate responses
Additional Notes 
The model does not have any moderation mechanisms, and may generate harmful or inappropriate responses. Follow the development on Twitter or join the Discord community for support.
Supported Languages 
Thai (on par with GPT-3.5), English (primary language)
LLM NameTyphoon 7B
Repository 🤗https://huggingface.co/scb10x/typhoon-7b 
Model Size7b
Required VRAM14.6 GB
Updated2024-12-26
Maintainerscb10x
Model Typemistral
Model Files  10.0 GB: 1-of-2   4.6 GB: 2-of-2   10.0 GB: 1-of-2   4.6 GB: 2-of-2
Supported Languagesth
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size35219
Torch Data Typebfloat16

Quantized Models of the Typhoon 7B

Model
Likes
Downloads
VRAM
Typhoon 7B GGUF1502 GB
Typhoon 7B GGUF8933 GB
Typhoon 7B GPTQ4364 GB
Typhoon 7B AWQ0234 GB

Best Alternatives to Typhoon 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25949
MegaBeam Mistral 7B 512K512K / 14.4 GB679146
SpydazWeb AI HumanAI RP512K / 14.4 GB311
SpydazWeb AI HumanAI 002512K / 14.4 GB201
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB325215
Hebrew Mistral 7B 200K256K / 30 GB304315
Astral 256K 7B V2250K / 14.4 GB180
Astral 256K 7B250K / 14.4 GB160
Boptruth Agatha 7B128K / 14.4 GB4750
Note: green Score (e.g. "73.2") means that the model is better than scb10x/typhoon-7b.

Rank the Typhoon 7B 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? 40248 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