Chaifighter 20B V3 by matchaaaaa

 ยป  All LLMs  ยป  matchaaaaa  ยป  Chaifighter 20B V3   URL Share it on

  Autotrain compatible Base model:merge:sao10k/fimbul... Base model:sao10k/fimbulvetr-1...   Endpoints compatible   Llama   Merge   Mergekit   Mistral   Region:us   Roleplay   Safetensors   Sharded   Tensorflow

Chaifighter 20B V3 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chaifighter 20B V3 (matchaaaaa/Chaifighter-20B-v3)

Chaifighter 20B V3 Parameters and Internals

Model Type 
text generation
Additional Notes 
Model was created using a combination of models, employing specific layer ranges and merging methods to enhance performance and mitigate stack damage issues.
Training Details 
Methodology:
Passthrough and linear merging methods using mergekit.
Context Length:
4096
Model Architecture:
Frankenmerge blend using input and output layers from different models.
Input Output 
Input Format:
Alpaca/Alpaca-based
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Temperature: 1.0 to 1.25, Min-P: 0.05 to 0.1, Repetition Penalty: 1.05 to 1.1, Rep. Penalty Range: 256 or 512.
LLM NameChaifighter 20B V3
Repository ๐Ÿค—https://huggingface.co/matchaaaaa/Chaifighter-20B-v3 
Base Model(s)  Fimbulvetr 11B V2   Sao10K/Fimbulvetr-11B-v2
Model Size11b
Required VRAM77.8 GB
Updated2025-01-15
Maintainermatchaaaaa
Model Typellama
Model Files  4.8 GB: 1-of-16   5.0 GB: 2-of-16   5.0 GB: 3-of-16   4.9 GB: 4-of-16   5.0 GB: 5-of-16   5.0 GB: 6-of-16   5.0 GB: 7-of-16   5.0 GB: 8-of-16   5.0 GB: 9-of-16   5.0 GB: 10-of-16   4.9 GB: 11-of-16   5.0 GB: 12-of-16   5.0 GB: 13-of-16   5.0 GB: 14-of-16   5.0 GB: 15-of-16   3.2 GB: 16-of-16
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.45.0.dev0
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Chaifighter 20B V3

Best Alternatives
Context / RAM
Downloads
Likes
...ral 11B Omni OP 1K 2048 Ver0.132K / 21.4 GB11250
MIstral 11B Omni OP U1k Ver0.132K / 21.4 GB11240
Llama 3 Synatra 11B V1 20K20K / 23 GB239
Fimbulvetr 11B V2.1 16K16K / 21.4 GB6817
Moistral 11B V28K / 21.4 GB5921
Moistral 11B V38K / 21.4 GB29394
Narumashi 11B V0.98K / 21.4 GB541
Moistral 11B V5d E48K / 21.4 GB151
Synaptica8K / 21.4 GB990
Moistral 11B V5c8K / 21.4 GB181
Note: green Score (e.g. "73.2") means that the model is better than matchaaaaa/Chaifighter-20B-v3.

Rank the Chaifighter 20B V3 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? 41363 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227