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

Chaifighter 20B by matchaaaaa

 »  All LLMs  »  matchaaaaa  »  Chaifighter 20B   URL Share it on

  67   
  Autotrain compatible Base model:finetune:sao10k/fim... Base model:sao10k/fimbulvetr-1...   En   Endpoints compatible   Llama   Merge   Mergekit   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/matchaaaaa/Chaifighter-20B 

Chaifighter 20B Benchmarks

LLME Score: 0.18802
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chaifighter 20B (matchaaaaa/Chaifighter-20B)

Chaifighter 20B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
long-form roleplay chats
Limitations:
Not ideal for short-form IRC/Discord RP chats
Additional Notes 
Chaifighter 20B is a frankenmerge of pre-trained language models.
Supported Languages 
en (high)
Training Details 
Methodology:
Passthrough merge method
Context Length:
4096
Hardware Used:
16 GB RTX 4060 Ti
Input Output 
Input Format:
Alpaca prompt template
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Temperature: 1.0 - 1.25, Min-P: 0.1, Repetition Penalty: 1.05-1.1, All other samplers disabled
LLM NameChaifighter 20B
Repository 🤗https://huggingface.co/matchaaaaa/Chaifighter-20B 
Base Model(s)  Fimbulvetr 11B V2   Sao10K/Fimbulvetr-11B-v2
Model Size11b
Required VRAM41.7 GB
Updated2025-02-22
Maintainermatchaaaaa
Model Typellama
Model Files  1.0 GB: 1-of-44   1.0 GB: 2-of-44   1.0 GB: 3-of-44   1.0 GB: 4-of-44   0.9 GB: 5-of-44   1.0 GB: 6-of-44   1.0 GB: 7-of-44   1.0 GB: 8-of-44   0.9 GB: 9-of-44   0.9 GB: 10-of-44   1.0 GB: 11-of-44   0.9 GB: 12-of-44   1.0 GB: 13-of-44   1.0 GB: 14-of-44   0.9 GB: 15-of-44   1.0 GB: 16-of-44   0.9 GB: 17-of-44   0.9 GB: 18-of-44   0.9 GB: 19-of-44   0.9 GB: 20-of-44   0.9 GB: 21-of-44   0.9 GB: 22-of-44   1.0 GB: 23-of-44   1.0 GB: 24-of-44   1.0 GB: 25-of-44   0.9 GB: 26-of-44   1.0 GB: 27-of-44   1.0 GB: 28-of-44   1.0 GB: 29-of-44   0.9 GB: 30-of-44   1.0 GB: 31-of-44   1.0 GB: 32-of-44   1.0 GB: 33-of-44   1.0 GB: 34-of-44   1.0 GB: 35-of-44   0.9 GB: 36-of-44   1.0 GB: 37-of-44   1.0 GB: 38-of-44   1.0 GB: 39-of-44   1.0 GB: 40-of-44   1.0 GB: 41-of-44   1.0 GB: 42-of-44   1.0 GB: 43-of-44   0.1 GB: 44-of-44
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-4.0
Context Length4096
Model Max Length4096
Transformers Version4.40.2
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Chaifighter 20B

Best Alternatives
Context / RAM
Downloads
Likes
...ral 11B Omni OP 1K 2048 Ver0.132K / 21.4 GB920
MIstral 11B Omni OP U1k Ver0.132K / 21.4 GB850
Llama 3 Synatra 11B V1 20K20K / 23 GB139
Fimbulvetr 11B V2.1 16K16K / 21.4 GB9417
Moistral 11B V28K / 21.4 GB5921
Moistral 11B V38K / 21.4 GB46897
Narumashi 11B V0.98K / 21.4 GB541
Moistral 11B V5d E48K / 21.4 GB151
Moistral 11B V5a8K / 21.4 GB201
Moistral 11B V5b8K / 21.4 GB121
Note: green Score (e.g. "73.2") means that the model is better than matchaaaaa/Chaifighter-20B.

Rank the Chaifighter 20B 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? 43470 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