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 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Typhoon 7B GPTQ   URL Share it on

  35   
  Arxiv:2312.13951   4-bit   Autotrain compatible Base model:quantized:scb10x/ty...   Base model:scb10x/typhoon-7b   Gptq   Mistral   Pretrained   Quantized   Region:us   Safetensors   Th
Model Card on HF 🤗: https://huggingface.co/TheBloke/typhoon-7B-GPTQ 

Typhoon 7B GPTQ Benchmarks

LLME Score: 0.15625
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Typhoon 7B GPTQ (TheBloke/typhoon-7B-GPTQ)

Typhoon 7B GPTQ Parameters and Internals

Model Type 
pretrained, decoder-only
Use Cases 
Limitations:
The model may not effectively follow human instructions without using few-shot learning or instruction fine-tuning., The model lacks moderation mechanisms and might produce harmful or inappropriate responses.
Additional Notes 
This is not an instruction-tuned model. The Instruct model (chat-model) will be released soon.
Supported Languages 
thai (high), english (high)
LLM NameTyphoon 7B GPTQ
Repository 🤗https://huggingface.co/TheBloke/typhoon-7B-GPTQ 
Model NameTyphoon 7B
Model CreatorSCB 10X
Base Model(s)  Typhoon 7B   scb10x/typhoon-7b
Model Size7b
Required VRAM4.2 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesth
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size35219
Torch Data Typebfloat16

Quantized Models of the Typhoon 7B GPTQ

Model
Likes
Downloads
VRAM
Typhoon 7B Chat Alpaca4240 GB

Best Alternatives to Typhoon 7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB39163850
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB86380
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB189618
...ephyr 7B Beta Channelwise Gptq32K / 4 GB99220
NeuralBeagle14 7B GPTQ32K / 4.2 GB169205
...baraHermes 2.5 Mistral 7B GPTQ32K / 4.2 GB370856
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB760
...phyr 7B Beta Assistant V1 Gptq32K / 4.2 GB791
...l Neural Chat 7B V3.8 Bit Gptq32K / 7.7 GB770
...lai Mistral 7B V0.1 4 Bit Gptq32K / 4.2 GB790
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/typhoon-7B-GPTQ.

Rank the Typhoon 7B 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? 42577 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 v20241227
  Support LLM Explorer