Typhoon 7B GGUF by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Typhoon 7B GGUF   URL Share it on

  Arxiv:2312.13951 Base model:quantized:scb10x/ty...   Base model:scb10x/typhoon-7b   Gguf   Mistral   Pretrained   Quantized   Region:us   Th

Typhoon 7B GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Typhoon 7B GGUF (TheBloke/typhoon-7B-GGUF)

Typhoon 7B GGUF Parameters and Internals

Model Type 
decoder-only, pretrained
Use Cases 
Primary Use Cases:
one/few-shot learning, instruction fine-tuning
Limitations:
may not follow human instructions, no moderation mechanisms, potentially harmful responses
Additional Notes 
Typhoon-7B is a pretrained model without instruction tuning. An instruction-tuned variant is in development.
Supported Languages 
primary (Thai), secondary (English)
LLM NameTyphoon 7B GGUF
Repository ๐Ÿค—https://huggingface.co/TheBloke/typhoon-7B-GGUF 
Model NameTyphoon 7B
Model CreatorSCB 10X
Base Model(s)  Typhoon 7B   scb10x/typhoon-7b
Model Size7b
Required VRAM3.1 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemistral
Model Files  3.1 GB   3.8 GB   3.5 GB   3.2 GB   4.1 GB   4.4 GB   4.2 GB   5.0 GB   5.2 GB   5.0 GB   6.0 GB   7.7 GB
Supported Languagesth
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Typhoon 7B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Pixel8K / 4.4 GB170
Mistral 7B Instruct V0.3 GGUF0K / 1.6 GB134849278
Qwen2 7B Instruct GGUF0K / 1.9 GB122074711
WizardLM 2 7B GGUF0K / 2.7 GB125636777
Deepthink Reasoning 7B GGUF0K / 4.7 GB163311
Conversely Mistral 7B0K / 0.2 GB1100
Mistral V0.3 7B Cybersecurity0K / 14.5 GB1401
QwQ LCoT 7B Instruct GGUF0K / 4.7 GB3699
Mistral 7B Instruct V0.3 GGUF0K / 2.7 GB646879
CleverBoi 7B V20K / 0.1 GB780
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/typhoon-7B-GGUF.

Rank the Typhoon 7B GGUF Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 42577 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227