Swallow 13B Instruct AWQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.5GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.1.
Swallow 13B Instruct AWQ Parameters and Internals
Model Type text generation, bilingual
Use Cases
Areas: Research, Commercial applications
Applications: Japanese and English text generation, Instruction following
Primary Use Cases: Text generation, Bilingual interaction
Limitations: Early stages without tuning for alignment with human intent and safety
Considerations: Follow ethical and responsible AI guidelines when using this model.
Additional Notes Quantized using AWQ method for faster processing while maintaining output quality.
Supported Languages Japanese (high), English (medium)
Training Details
Data Sources: Japanese Wikipedia, RefinedWeb, Swallow Corpus, The Pile, Anthropic HH-RLHF, Databricks Dolly 15-k, OpenAssistant Conversations Dataset
Methodology: Supervised fine-tuning (SFT)
Context Length: Hardware Used: Hardware provided by Massed Compute
Model Architecture: Transformer-based architecture, specific details according to LLaMA-2 technical report
Input Output
Input Format: Japanese or English text instructions
Accepted Modalities: Output Format: Text generation based on prompts
Performance Tips: Utilize appropriate quantization level and adjust sampling parameters for better performance.
LLM Name Swallow 13B Instruct AWQ Repository 🤗 https://huggingface.co/TheBloke/Swallow-13B-Instruct-AWQ Model Name Swallow 13B Instruct Model Creator tokyotech-llm Base Model(s) Swallow 13B Instruct Hf tokyotech-llm/Swallow-13b-instruct-hf Model Size 13b Required VRAM 7.5 GB Updated 2026-08-04 Maintainer TheBloke Model Type llama Instruction-Based Yes Model Files 7.5 GB Supported Languages en ja AWQ Quantization Yes Quantization Type awq Model Architecture LlamaForCausalLM License llama2 Context Length 4096 Model Max Length 4096 Transformers Version 4.35.2 Tokenizer Class LlamaTokenizer Beginning of Sentence Token <s> End of Sentence Token </s> Unk Token <unk> Vocabulary Size 43176 Torch Data Type float16
Rank the Swallow 13B Instruct AWQ capabilities
Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.
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
Best Alternatives to Swallow 13B Instruct AWQ
Note: green Score (e.g. "73.2 ") means that the model is better than TheBloke/Swallow-13B-Instruct-AWQ .
Expand