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

Augmental 13B V1.50 B by Heralax

 »  All LLMs  »  Heralax  »  Augmental 13B V1.50 B   URL Share it on

  108   
  Autotrain compatible   Endpoints compatible   F16   Ggml   Gguf   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Heralax/Augmental-13b-v1.50_B 

Augmental 13B V1.50 B Benchmarks

LLME Score: 0.14466
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Augmental 13B V1.50 B (Heralax/Augmental-13b-v1.50_B)

Augmental 13B V1.50 B Parameters and Internals

Model Type 
roleplay, augmentative RP dataset
Use Cases 
Areas:
roleplaying, storytelling
Applications:
chat applications, creative writing
Limitations:
Potential bias toward trained characters, Unfamiliarity with contexts outside trained data
Additional Notes 
Augmental-13b excels at long responses due to augmented training data.
Supported Languages 
English (fluent)
Training Details 
Data Sources:
Steins;Gate visual novel
Data Volume:
8000 AI-enhanced lines
Methodology:
Merging MythoMax at 0.33% weighting, GPT-4 augmentations
Model Architecture:
Based on MythoMax with merging and augmentation processes
Input Output 
Input Format:
SillyTavern
Output Format:
longer responses
Release Notes 
Version:
1.50 B
Notes:
Improved coherency and distinctiveness by merging MythoMax at 0.33% weighting.
Version:
1.50 A
Notes:
Addressed undertraining issues with different hyperparameters and MythoMax merging.
Version:
1.0
Notes:
Initial release, identified coherency issues after early feedback and testing.
LLM NameAugmental 13B V1.50 B
Repository 🤗https://huggingface.co/Heralax/Augmental-13b-v1.50_B 
Model Size13b
Required VRAM26.1 GB
Updated2025-02-05
MaintainerHeralax
Model Typellama
Model Files  9.2 GB   26.0 GB   10.0 GB: 1-of-3   10.0 GB: 2-of-3   6.1 GB: 3-of-3
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Quantized Models of the Augmental 13B V1.50 B

Model
Likes
Downloads
VRAM
Augmental 13B V1.50 B GGUF31755 GB
Augmental 13B V1.50 B GPTQ1187 GB
Augmental 13B V1.50 B AWQ1107 GB

Best Alternatives to Augmental 13B V1.50 B

Best Alternatives
Context / RAM
Downloads
Likes
Chinese Llama 2 13B Gguf64K / 5 GB4445
...ama Instruct 13B Alpaca Lora6416K / 26 GB80
... Codellama Instruct 13B Lora6416K / 26 GB70
... Instruct 13B Alpacamod Lora6416K / 26 GB60
Openthaigpt 1.0.0 13B Chat4K / 26.2 GB2086
Estopian4K / 26 GB150
BioinspiredLLM4K / 26 GB1725
Orca 2 13B GGUF4K / 5.4 GB2807
Cat 0.54K / 26 GB10813
Augmental 13B V1.50 A4K / 26.1 GB751
Note: green Score (e.g. "73.2") means that the model is better than Heralax/Augmental-13b-v1.50_B.

Rank the Augmental 13B V1.50 B 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? 42625 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