Tofu 3B by jeiku

 ยป  All LLMs  ยป  jeiku  ยป  Tofu 3B   URL Share it on

  Merged Model   Arxiv:2212.04089   Autotrain compatible Base model:jeiku/alpaca 128 st... Base model:jeiku/bluemoon clea... Base model:jeiku/everything v3... Base model:jeiku/gnosis 256 st... Base model:jeiku/limarp stable... Base model:jeiku/no robots alp... Base model:jeiku/pippa 128 sta...   Base model:jeiku/rosa v1 3b Base model:jeiku/rpgpt stablel... Base model:jeiku/theory of min... Base model:jeiku/theory of min... Base model:jeiku/toxic dpo sta...   Conversational   Custom code   Region:us   Safetensors   Sharded   Stablelm epoch   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/jeiku/Tofu_3B 

Tofu 3B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tofu 3B (jeiku/Tofu_3B)

Tofu 3B Parameters and Internals

Model Type 
language model
Additional Notes 
This model is a merge of various pre-trained language models using task arithmetic methods. The configuration used includes weights for different model combinations.
Training Details 
Methodology:
task_arithmetic merge
LLM NameTofu 3B
Repository ๐Ÿค—https://huggingface.co/jeiku/Tofu_3B 
Base Model(s)  Rosa V1 3B   Theory Of Mind 128 StableLM   Rosa V1 3B   Rosa V1 3B   jeiku/PIPPA_128_StableLM   Rosa V1 3B   jeiku/LimaRP_StableLM   Rosa V1 3B   Theory Of Mind RP 128 StableLM   Rosa V1 3B   No Robots Alpaca StableLM   Rosa V1 3B   jeiku/Alpaca_128_StableLM   Rosa V1 3B   jeiku/Everything_v3_128_StableLM   Rosa V1 3B   jeiku/RPGPT_StableLM   Rosa V1 3B   Toxic DPO StableLM   Rosa V1 3B   jeiku/Gnosis_256_StableLM   Rosa V1 3B   Bluemoon Cleaned StableLM   jeiku/Rosa_v1_3B   jeiku/Theory_of_Mind_128_StableLM   jeiku/Rosa_v1_3B   jeiku/Rosa_v1_3B   jeiku/PIPPA_128_StableLM   jeiku/Rosa_v1_3B   jeiku/LimaRP_StableLM   jeiku/Rosa_v1_3B   jeiku/Theory_of_Mind_RP_128_StableLM   jeiku/Rosa_v1_3B   jeiku/No_Robots_Alpaca_StableLM   jeiku/Rosa_v1_3B   jeiku/Alpaca_128_StableLM   jeiku/Rosa_v1_3B   jeiku/Everything_v3_128_StableLM   jeiku/Rosa_v1_3B   jeiku/RPGPT_StableLM   jeiku/Rosa_v1_3B   jeiku/Toxic_DPO_StableLM   jeiku/Rosa_v1_3B   jeiku/Gnosis_256_StableLM   jeiku/Rosa_v1_3B   jeiku/Bluemoon_cleaned_StableLM
Merged ModelYes
Model Size3b
Required VRAM5.6 GB
Updated2024-12-23
Maintainerjeiku
Model Typestablelm_epoch
Model Files  5.6 GB: 1-of-1
Model ArchitectureStableLMEpochForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|endoftext|>
Vocabulary Size50304
Torch Data Typefloat16

Best Alternatives to Tofu 3B

Best Alternatives
Context / RAM
Downloads
Likes
Stable Code 3B Mlx16K / 5.6 GB91
Aura 3B4K / 5.6 GB112
Slim Extract4K / 5.6 GB2512
Slim Boolean4K / 5.6 GB194
Slim Summary4K / 5.6 GB597
Slim Tags 3B4K / 5.6 GB124
Slim Sa Ner4K / 5.6 GB86
Slim Xsum4K / 5.6 GB56
Memphis CoT 3B4K / 5.6 GB7329
Fett Uccine Mini 3B4K / 5.6 GB123
Note: green Score (e.g. "73.2") means that the model is better than jeiku/Tofu_3B.

Rank the Tofu 3B 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? 40126 in total.

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