Swallow 70B Instruct AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Swallow 70B Instruct AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:quantized:tokyotech... Base model:tokyotech-llm/swall...   En   Instruct   Ja   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Swallow 70B Instruct AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Swallow 70B Instruct AWQ (TheBloke/Swallow-70B-instruct-AWQ)

Swallow 70B Instruct AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Applications:
Research, Commercial applications
Additional Notes 
The Swallow model is mainly tuned for Japanese language data and features modified vocabulary to enhance inference speed.
Supported Languages 
languages_supported (>2 including Japanese and English.), proficiency_notes (>Proficient in Japanese and English.)
Training Details 
Data Sources:
Japanese Wikipedia, RefinedWeb, Swallow Corpus, The Pile
Methodology:
Supervised fine-tuning (SFT)
Context Length:
4096
Model Architecture:
Llama
Input Output 
Input Format:
Formatted Japanese instructions and prompts.
Accepted Modalities:
Text
Output Format:
Generated textual response
LLM NameSwallow 70B Instruct AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Swallow-70B-instruct-AWQ 
Model NameSwallow 70B Instruct
Model Creatortokyotech-llm
Base Model(s)  Swallow 70B Instruct Hf   tokyotech-llm/Swallow-70b-instruct-hf
Model Size70b
Required VRAM37 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-4   10.0 GB: 2-of-4   9.9 GB: 3-of-4   7.2 GB: 4-of-4
Supported Languagesen ja
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size43176
Torch Data Typefloat16

Best Alternatives to Swallow 70B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...0B Instruct Gradient 1048K AWQ1024K / 39.9 GB121
...70B Instruct Gradient 262K AWQ256K / 39.9 GB110
Llama 3.3 70B Instruct AWQ128K / 39.9 GB2078018
...lama 3.3 70B Instruct AWQ INT4128K / 39.9 GB751010
... SauerkrautLM 70B Instruct AWQ128K / 39.9 GB16034
Llama 3 70B Instruct AWQ8K / 39.9 GB1307568
Meta Llama 3 70B Instruct AWQ8K / 39.9 GB141
Llama 3 70B Instruct AWQ8K / 39.9 GB161
...Typhoon V1.5x 70B Instruct AWQ8K / 39.9 GB332
... Llama 3 70B Instruct AWQ GEMM8K / 39.9 GB170
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Swallow-70B-instruct-AWQ.

Rank the Swallow 70B Instruct AWQ 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? 40123 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217