LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Superswallow 70B V0.1 by nitky

What open-source LLMs or SLMs are you in search of? 18732 in total.

 ยป  All LLMs  ยป  nitky  ยป  Superswallow 70B V0.1   URL Share it on

  Merged Model   Arxiv:2306.01708   Arxiv:2311.03099   Arxiv:2311.10702   Autotrain compatible Base model:allenai/tulu-2-dpo-... Base model:tokyotech-llm/swall...   En   Endpoints compatible   Has space   Instruct   Ja   License:llama2   Llama   Region:us   Safetensors   Sharded   Tensorflow

Rank the Superswallow 70B V0.1 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  
Superswallow 70B V0.1 (nitky/Superswallow-70b-v0.1)

Best Alternatives to Superswallow 70B V0.1

Best Alternatives
HF Rank
Dolphin 2.2 70B70.64K / 138 GB192943
SOLAR 0 70B 16bit70.114K / 138 GB2953250
Platypus2 70B Instruct69.34K / 138 GB3235172
MegaDolphin 120B68.914K / 240.7 GB242359
ORCA LLaMA 70B QLoRA67.64K / 138 GB219752
Platypus QLoRA LLaMA 70b67.574K / 138 GB21303
Llama 2 70B Instruct67.382K / 138 GB195162
Instruct Llama70B Dolly15k66.424K / 138 GB35760
Swallow 70B Instruct Hf65.744K / 139.1 GB1058933
Dolphin 2.2 70B GPTQ61.94K / 35.3 GB45
Note: green Score (e.g. "73.2") means that the model is better than nitky/Superswallow-70b-v0.1.

Superswallow 70B V0.1 Parameters and Internals

LLM NameSuperswallow 70B V0.1
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Tulu 2 DPO 70B   Swallow 70B Instruct Hf   allenai/tulu-2-dpo-70b   tokyotech-llm/Swallow-70b-instruct-hf
Merged ModelYes
Model Size70b
Required VRAM138.4 GB
Model Typellama
Model Files  9.6 GB: 1-of-15   10.0 GB: 2-of-15   9.8 GB: 3-of-15   9.7 GB: 4-of-15   9.6 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   10.0 GB: 10-of-15   9.8 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.7 GB: 14-of-15   1.2 GB: 15-of-15
Supported Languagesen ja
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size43176
Initializer Range0.02
Torch Data Typebfloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003