J.O.S.I.E.3 Beta12 7B Slerp by Isaak-Carter

 ยป  All LLMs  ยป  Isaak-Carter  ยป  J.O.S.I.E.3 Beta12 7B Slerp   URL Share it on

  Merged Model Argilla/capybarahermes-2.5-mis...   Autotrain compatible Base model:argilla/capybaraher... Base model:weyaxi/einstein-v6-...   Conversational   De   En   Endpoints compatible   Es   Fr   Ja   License:apache-2.0   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Weyaxi/einstein-v6-7b   Zh

Rank the J.O.S.I.E.3 Beta12 7B Slerp 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  
J.O.S.I.E.3 Beta12 7B Slerp (Isaak-Carter/J.O.S.I.E.3-Beta12-7B-slerp)

Best Alternatives to J.O.S.I.E.3 Beta12 7B Slerp

Best Alternatives
HF Rank
KAI 7B V0.174.4532K / 14.4 GB559
Dolphin 2.2.1 Mistral 7B73.1732K / 14.4 GB11623185
Notus 7B V160.1532K / 14.4 GB9271112
Notus 7B V1 AWQ52.832K / 4.2 GB443
Notus 7B V1 GPTQ52.832K / 4.2 GB422
MegaBeam Mistral 7B 300K282K / 14.4 GB27868
Hebrew Mistral 7B 200K256K / 30 GB54514
Astral 256K 7B V2250K / 14.4 GB6330
Astral 256K 7B250K / 14.4 GB6250
Buddhi 128K Chat 7B128K / 14.4 GB366311
Note: green Score (e.g. "73.2") means that the model is better than Isaak-Carter/J.O.S.I.E.3-Beta12-7B-slerp.

J.O.S.I.E.3 Beta12 7B Slerp Parameters and Internals

LLM NameJ.O.S.I.E.3 Beta12 7B Slerp
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Einstein V6 7B   CapybaraHermes 2.5 Mistral 7B   Weyaxi/Einstein-v6-7B   argilla/CapybaraHermes-2.5-Mistral-7B
Merged ModelYes
Model Size7b
Required VRAM14.4 GB
Model Typemistral
Model Files  2.0 GB: 1-of-8   1.9 GB: 2-of-8   2.0 GB: 3-of-8   2.0 GB: 4-of-8   1.9 GB: 5-of-8   1.9 GB: 6-of-8   1.9 GB: 7-of-8   0.8 GB: 8-of-8
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34817 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801