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

Augmental Unholy 13B by Heralax

 »  All LLMs  »  Heralax  »  Augmental Unholy 13B   URL Share it on

  14   

Augmental Unholy 13B is an open-source language model by Heralax. Features: 13b LLM, VRAM: 26GB, Quantized, LLM Explorer Score: 0.1.

  Arxiv:1910.09700   Adapter Base model:adapter:undi95/unho... Base model:undi95/unholy-v1-10...   Endpoints compatible   F16   Finetuned   Ggml   Gguf   Llama   Lora   Peft   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Heralax/Augmental-Unholy-13b 

Augmental Unholy 13B Benchmarks

LLME Score: 0.10352
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Augmental Unholy 13B (Heralax/Augmental-Unholy-13b)
🌟 Advertise your project 🚀

Augmental Unholy 13B Parameters and Internals

Training Details 
Methodology:
The following `bitsandbytes` quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16
LLM NameAugmental Unholy 13B
Repository 🤗https://huggingface.co/Heralax/Augmental-Unholy-13b 
Base Model(s)  Undi95/Unholy-v1-10L-13B   Undi95/Unholy-v1-10L-13B
Model Size13b
Required VRAM26 GB
Updated2026-03-29
MaintainerHeralax
Model Files  0.1 GB   9.2 GB   26.0 GB   9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3   0.0 GB
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typeggml|gguf
Model ArchitectureAdapter
Is Biasednone
Tokenizer ClassLlamaTokenizer
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj|v_proj|gate_proj|up_proj|o_proj|q_proj|k_proj
LoRA Alpha8
LoRA Dropout0.05
R Param4

Quantized Models of the Augmental Unholy 13B

Model
Likes
Downloads
VRAM
Augmental Unholy 13B GPTQ657 GB
Augmental Unholy 13B AWQ157 GB

Best Alternatives to Augmental Unholy 13B

Best Alternatives
Context / RAM
Downloads
Likes
...n Llama 13B Lora Cabra Adapter0K / 0 GB162
Storytelling V2 13B Lora0K / 0.5 GB57
Lmg V3 Lora0K / 0.5 GB72
Storytelling V1 13B Lora0K / 0.5 GB06
Minotaur Llama2 13B Qlora0K / 1 GB114
Minotaur Llama2 13B Qlora0K / 1 GB34
Llama 13B 4bit Alpaca0K / 0.1 GB31
Llama 2 13B 4bit Alpaca Gpt40K / 0 GB52
Alpaca Lora 13B 4bit0K / 0 GB01
Alpaca1337 13B 4bit0K / 0 GB04

Rank the Augmental Unholy 13B 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? 52473 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