OpenChat 3.5 0106 9.86B 44Layers Appended by Pretergeek

 ยป  All LLMs  ยป  Pretergeek  ยป  OpenChat 3.5 0106 9.86B 44Layers Appended   URL Share it on

  Merged Model   Arxiv:2401.02415   Autotrain compatible Base model:finetune:openchat/o... Base model:openchat/openchat-3...   Conversational   Endpoints compatible   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow

OpenChat 3.5 0106 9.86B 44Layers Appended Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OpenChat 3.5 0106 9.86B 44Layers Appended (Pretergeek/OpenChat-3.5-0106_9.86B_44Layers-Appended)

OpenChat 3.5 0106 9.86B 44Layers Appended Parameters and Internals

Model Type 
text generation
Additional Notes 
This model is created using [mergekit] passing through merge method and employing Block Expansion method enhancing the understanding of existing tasks.
Training Details 
Methodology:
The model employs a variation of the Block Expansion method. New layers are added to the end of the model while original layers are frozen, allowing the new layers to be trained or fine-tuned separately, minimizing catastrophic forgetting.
Model Architecture:
Passthrough merge method with Block Expansion, adding new layers to the end of the model.
LLM NameOpenChat 3.5 0106 9.86B 44Layers Appended
Repository ๐Ÿค—https://huggingface.co/Pretergeek/OpenChat-3.5-0106_9.86B_44Layers-Appended 
Base Model(s)  openchat/openchat-3.5-0106   openchat/openchat-3.5-0106
Merged ModelYes
Model Size9.86b
Required VRAM19.7 GB
Updated2024-12-22
MaintainerPretergeek
Model Typemistral
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.9 GB: 3-of-4   5.0 GB: 4-of-4
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.42.4
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typebfloat16

Rank the OpenChat 3.5 0106 9.86B 44Layers Appended 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? 40066 in total.

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