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

OpenChat 3.5 0106 9.86B 44Layers Appended by Pretergeek

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

  4   

OpenChat 3.5 0106 9.86B 44Layers Appended is an open-source language model by Pretergeek. Features: 9.86b LLM, VRAM: 19.7GB, Context: 8K, License: apache-2.0, Merged, LLM Explorer Score: 0.21.

  Merged Model   Arxiv:2401.02415 Base model:finetune:openchat/o... Base model:openchat/openchat-3...   Conversational   Endpoints compatible   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Pretergeek/OpenChat-3.5-0106_9.86B_44Layers-Appended 

OpenChat 3.5 0106 9.86B 44Layers Appended Benchmarks

MMLU Pro: 25.44
GPQA: 7.61
MUSR: 11.78
BBH: 24.06
IFEval: 59.61 vs 88 (so35)-32.3%
MATH Lvl 5: 7.93
LLME Score: 0.21102
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)
🌟 Advertise your project 🚀

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 🤗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
Updated2026-04-11
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

🆘 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer