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

Typhoon V1.5 72B Instruct AWQ by scb10x

 »  All LLMs  »  scb10x  »  Typhoon V1.5 72B Instruct AWQ   URL Share it on

  30   
  Arxiv:2312.13951   4-bit   Autotrain compatible   Awq   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/scb10x/typhoon-v1.5-72b-instruct-awq 

Typhoon V1.5 72B Instruct AWQ Benchmarks

LLME Score: 0.1958
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Typhoon V1.5 72B Instruct AWQ (scb10x/typhoon-v1.5-72b-instruct-awq)

Typhoon V1.5 72B Instruct AWQ Parameters and Internals

Model Type 
instruct, decoder-only model
Use Cases 
Limitations:
undergoing development, capable of inaccurate, biased, or objectionable answers
Considerations:
Developers should assess risks in the context of their use case.
Additional Notes 
This model is an instructional model, incorporating some level of guardrails.
Supported Languages 
th (Thai), en (English)
Input Output 
Input Format:
chatml chat-template
Accepted Modalities:
text
Output Format:
response to input prompt
LLM NameTyphoon V1.5 72B Instruct AWQ
Repository 🤗https://huggingface.co/scb10x/typhoon-v1.5-72b-instruct-awq 
Base Model(s)  scb10x/typhoon-v1.5-72b-instruct   scb10x/typhoon-v1.5-72b-instruct
Model Size72b
Required VRAM41.3 GB
Updated2024-12-26
Maintainerscb10x
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   5.0 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   5.0 GB: 7-of-9   3.8 GB: 8-of-9   2.5 GB: 9-of-9
Supported Languagesth en
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Typhoon V1.5 72B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 72B Instruct AWQ32K / 41.6 GB10971751
Qwen2 72B Instruct AWQ32K / 41.6 GB1669237
Athene V2 Chat AWQ32K / 41.6 GB1324
Qwen2 72B Instruct AWQ GEMM32K / 41.6 GB130
ECE ILAB Q132K / 77.8 GB25360
Qwen2.5 72B Instruct 4bit32K / 40.9 GB364913
Qwen2.5 72B Instruct Bnb 4bit32K / 41.4 GB68793
Athene V2 Chat 4.65bpw H6 EXL232K / 44.3 GB976
Qwen2.5 72B Instruct 8bit32K / 77.1 GB914
Qwen2 72B Instruct Bnb 4bit32K / 41.2 GB3617
Note: green Score (e.g. "73.2") means that the model is better than scb10x/typhoon-v1.5-72b-instruct-awq.

Rank the Typhoon V1.5 72B Instruct 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? 40303 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