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

Openthaigpt1.5 7B Instruct by openthaigpt

 »  All LLMs  »  openthaigpt  »  Openthaigpt1.5 7B Instruct   URL Share it on

  3638   
  Arxiv:2309.00071   Arxiv:2411.07238   Autotrain compatible   Conversational   Doi:10.57967/hf/3168   En   Endpoints compatible   Gguf   Instruct   Model-index   Openthaigpt   Quantized   Qwen   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct 

Openthaigpt1.5 7B Instruct Benchmarks

LLME Score: 0.21565
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openthaigpt1.5 7B Instruct (openthaigpt/openthaigpt1.5-7b-instruct)
🌟 Advertise your project 🚀

Openthaigpt1.5 7B Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Thai language instruction-based chat
Primary Use Cases:
Thai-specific domain question answering, Multi-turn conversations, Retrieval Augmented Generation (RAG) compatibility
Supported Languages 
th (native), en (native)
Training Details 
Data Sources:
Thai instruction pairs
Data Volume:
over 2,000,000 pairs
Methodology:
Fine-tuning
Context Length:
131072
Model Architecture:
Based on Qwen
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Enables RAG compatibility for enhanced response generation
LLM NameOpenthaigpt1.5 7B Instruct
Repository 🤗https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct 
Model Size7b
Required VRAM15.2 GB
Updated2025-09-23
Maintaineropenthaigpt
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4   15.2 GB   3.8 GB   4.7 GB
Supported Languagesth en
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Openthaigpt1.5 7B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 Cantonese 7B Instruct32K / 15.4 GB833
Qwen 2.5 7B Threatflux32K / 15.5 GB276
...der 7B Instruct Abliterated V132K / 15.2 GB32
Qwen2 7B Instruct GGUF32K / 3 GB12331
Qwen2 7B Instruct GGUF32K / 3 GB170
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB113710
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB773
Qwen2.5 7B Instruct 1M 8bit986K / 8.1 GB153
Qwen2.5 7B Instruct 1M 6bit986K / 6.2 GB102
Alisia 7B Instruct V1128K / 15.4 GB1142
Note: green Score (e.g. "73.2") means that the model is better than openthaigpt/openthaigpt1.5-7b-instruct.

Rank the Openthaigpt1.5 7B Instruct 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? 51544 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