LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Excalibur 7B by InferenceIllusionist

 »  All LLMs  »  InferenceIllusionist  »  Excalibur 7B   URL Share it on

  13   
  Merged Model   Autotrain compatible Base model:bardsai/jaskier-7b-...   Base model:ibm/merlinite-7b Base model:inferenceillusionis...   Base model:mlabonne/monarch-7b Base model:sanjiwatsuki/kunoic...   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Excalibur 7B Benchmarks

ARC: 69.71 vs 96.7 (so35)-27.9%
HellaSwag: 87.56 vs 95.3 (gpt4)-8.1%
MMLU: 65.66 vs 88.3 (so35)-25.6%
TruthfulQA: 67.24 vs 59 (gpt4)14%
WinoGrande: 82.79 vs 87.5 (gpt4)-5.4%
GSM8K: 68.61 vs 96.4 (so35)-28.8%
LLME Score: 0.21232
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Excalibur 7B Parameters and Internals

LLM NameExcalibur 7B
Repository 🤗https://huggingface.co/InferenceIllusionist/Excalibur-7b 
Base Model(s)  Merlinite 7B   Magic Dolphin 7B   Kunoichi DPO V2 7B   Monarch 7B   bardsai/jaskier-7b-dpo-v6.1   ibm/merlinite-7b   InferenceIllusionist/Magic-Dolphin-7b   SanjiWatsuki/Kunoichi-DPO-v2-7B   mlabonne/Monarch-7B   bardsai/jaskier-7b-dpo-v6.1
Merged ModelYes
Model Size7b
Required VRAM14.4 GB
Updated2024-09-08
MaintainerInferenceIllusionist
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16
Excalibur 7B (InferenceIllusionist/Excalibur-7b)

Best Alternatives to Excalibur 7B

Best Alternatives
Context / RAM
Downloads
Likes
MegaBeam Mistral 7B 512K512K / 14.4 GB5688838
...daz Web AI ChatML 512K Project512K / 14.5 GB170
MegaBeam Mistral 7B 300K282K / 14.4 GB23715
Hebrew Mistral 7B 200K256K / 30 GB270415
Astral 256K 7B V2250K / 14.4 GB80
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB230
Test002128K / 29 GB160
Buddhi 128K Chat 7B128K / 14.4 GB16715
LuminRP 7B 128K V0.2128K / 14.4 GB140
Note: green Score (e.g. "73.2") means that the model is better than InferenceIllusionist/Excalibur-7b.

Rank the Excalibur 7B Capabilities

🆘 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! 🌟

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? 35693 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803
  Support LLM Explorer