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

ChanMalion by TehVenom

 »  All LLMs  »  TehVenom  »  ChanMalion   URL Share it on

  1937   
  Autotrain compatible   Endpoints compatible   Gptj   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TehVenom/ChanMalion 

ChanMalion Benchmarks

ARC: 41.89 vs 96.7 (so35)-56.7%
HellaSwag: 68.25 vs 95.3 (gpt4)-28.4%
MMLU: 27.29 vs 88.3 (so35)-69.1%
TruthfulQA: 33.89 vs 59 (gpt4)-42.6%
WinoGrande: 65.35 vs 87.5 (gpt4)-25.3%
GSM8K: 1.67 vs 96.4 (so35)-98.3%
LLME Score: 0.12676
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ChanMalion (TehVenom/ChanMalion)
🌟 Advertise your project 🚀

ChanMalion Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
community-driven projects, experimentation
Limitations:
Potential bias due to training data, Not suitable for all conversational contexts
Considerations:
Caution advised in use due to mixed training data origins
Additional Notes 
Given its mixed training corpus, the model exhibits unique behavior influenced by the distinct datasets. The merging of 4Chan and Pygmalion-6b provides a wide range of conversational abilities, but biases from both datasets must be considered.
Training Details 
Data Sources:
4Chan posts, Pygmalion dataset
Methodology:
Intermediate merging of GPT-J trained on 4Chan data with Pygmalion-6b model
Model Architecture:
Transformer-based architecture
LLM NameChanMalion
Repository 🤗https://huggingface.co/TehVenom/ChanMalion 
Required VRAM12.3 GB
Updated2025-08-17
MaintainerTehVenom
Model Typegptj
Model Files  2.1 GB: 1-of-6   2.1 GB: 2-of-6   2.1 GB: 3-of-6   2.1 GB: 4-of-6   2.0 GB: 5-of-6   1.9 GB: 6-of-6
Model ArchitectureGPTJForCausalLM
Model Max Length1024
Transformers Version4.25.0.dev0
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50400
Torch Data Typefloat16
Activation Functiongelu_new
Errorsreplace

Best Alternatives to ChanMalion

Best Alternatives
Context / RAM
Downloads
Likes
DiffMerge DollyGPT Pygmalion0K / 12.1 GB19272
...Merge Pygmalion Main Onto V8P40K / 12.3 GB19271
Javalion GPTJ0K / 12.3 GB17931
Skegma GPTJ0K / 12.3 GB17770
Javalion R0K / 12.3 GB17915
Adventien GPTJ0K / 12.3 GB17950
Janin GPTJ0K / 12.3 GB17950
Javelin R0K / 12.3 GB17812
Javelin GPTJ0K / 12.3 GB17854
Janin R0K / 12.3 GB17751
Note: green Score (e.g. "73.2") means that the model is better than TehVenom/ChanMalion.

Rank the ChanMalion 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? 50723 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 v20241124
  Support LLM Explorer