Hathor V3.5 by MrRobotoAI

 ยป  All LLMs  ยป  MrRobotoAI  ยป  Hathor V3.5   URL Share it on

  Merged Model   Arxiv:2311.03099   Autotrain compatible Base model:mrrobotoai/hathor-v... Base model:mrrobotoai/hathor-v... Base model:mrrobotoai/hathor-v...   Custom code   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/MrRobotoAI/Hathor-v3.5 

Hathor V3.5 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hathor V3.5 (MrRobotoAI/Hathor-v3.5)

Hathor V3.5 Parameters and Internals

Additional Notes 
This is a merged model using the DARE linear merge method. The configuration involves MrRobotoAI/Hathor-v4 with a weight of 0.55 and density of 0.9, and MrRobotoAI/Hathor-v3.4 with a weight of 0.45 and density of 0.9, normalized to float16 data type.
LLM NameHathor V3.5
Repository ๐Ÿค—https://huggingface.co/MrRobotoAI/Hathor-v3.5 
Base Model(s)  MrRobotoAI/Hathor-v3.4   MrRobotoAI/Hathor-v4.1   Hathor V4   MrRobotoAI/Hathor-v3.4   MrRobotoAI/Hathor-v4.1   MrRobotoAI/Hathor-v4
Merged ModelYes
Model Size7.2b
Required VRAM14.5 GB
Updated2024-11-11
MaintainerMrRobotoAI
Model Typemistral
Model Files  4.9 GB: 1-of-3   4.9 GB: 2-of-3   4.7 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.44.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Hathor V3.5

Best Alternatives
Context / RAM
Downloads
Likes
...Web AI HumanAI 012 INSTRUCT XA512K / 14.4 GB130
...Web AI HumanAI 012 INSTRUCT IA512K / 14.4 GB140
...Web AI HumanAI 011 INSTRUCT ML512K / 14.4 GB180
...dazWeb AI HumanAI 011 INSTRUCT512K / 14.4 GB231
SpydazWeb HumanAI M2512K /  GB380
SpydazWeb AI HumanAI 009 CHAT512K / 14.4 GB110
...Web AI HumanAI 012 INSTRUCT MX512K / 14.4 GB120
SpydazWeb AI HumanAI 010 CHAT512K / 14.4 GB100
SpydazWeb AI HumanAI 007512K / 14.4 GB60
SpydazWebAI Human AGI512K / 14.5 GB162
Note: green Score (e.g. "73.2") means that the model is better than MrRobotoAI/Hathor-v3.5.

Rank the Hathor V3.5 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? 41470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227