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

Ende Chat 0.0.5 by kno10

 »  All LLMs  »  kno10  »  Ende Chat 0.0.5   URL Share it on

  7   
  Autotrain compatible   Conversational Dataset:freedomintelligence/sh... Dataset:mayflowergmbh/airoboro... Dataset:mayflowergmbh/alpaca-g... Dataset:mayflowergmbh/dolly 15... Dataset:mayflowergmbh/dolphin ... Dataset:mayflowergmbh/evol ins...   Dataset:mayflowergmbh/oasst de Dataset:mayflowergmbh/openschn... Dataset:mayflowergmbh/ultracha... Dataset:wizardlm/wizardlm evol...   De   En   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kno10/ende-chat-0.0.5 

Ende Chat 0.0.5 Benchmarks

MMLU Pro: 8.78
GPQA: 2.01
MUSR: 7.1
BBH: 11.13
IFEval: 34.04 vs 88 (so35)-61.3%
MATH Lvl 5: 0.76
LLME Score: 0.22754
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ende Chat 0.0.5 (kno10/ende-chat-0.0.5)

Ende Chat 0.0.5 Parameters and Internals

Model Type 
Language model, Chat model
Use Cases 
Areas:
Chat in German and English
Limitations:
Not received alignment or comprehensive instruction finetuning
Additional Notes 
This model is a proof of concept and further finetuning is necessary. It is not fully evaluated and most fine-tuning data is automatically translated from English, which may not lead to high-quality data.
Supported Languages 
deu (German language support), eng (English language support)
Training Details 
Data Sources:
Proprietary text collected from the internet
Data Volume:
Limited due to GPU constraints
Methodology:
LoRA finetuning; initial finetuning with English and German data
Context Length:
1024
Hardware Used:
2xV100 GPU
Model Architecture:
Mistral-7B
LLM NameEnde Chat 0.0.5
Repository 🤗https://huggingface.co/kno10/ende-chat-0.0.5 
Model Size7.9b
Required VRAM15.8 GB
Updated2025-02-05
Maintainerkno10
Model Typemistral
Instruction-BasedYes
Model Files  4.0 GB: 1-of-4   4.0 GB: 2-of-4   3.9 GB: 3-of-4   3.9 GB: 4-of-4
Supported Languagesen de
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizerFast
Padding Token</s>
Vocabulary Size111235
Torch Data Typefloat16

Best Alternatives to Ende Chat 0.0.5

Best Alternatives
Context / RAM
Downloads
Likes
Ende Chat 0.0.732K / 15.8 GB50
Note: green Score (e.g. "73.2") means that the model is better than kno10/ende-chat-0.0.5.

Rank the Ende Chat 0.0.5 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? 42577 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 v20241227
  Support LLM Explorer