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

Alpacino30b by digitous

 »  All LLMs  »  digitous  »  Alpacino30b   URL Share it on

  25   
  Alpaca   Autotrain compatible   Endpoints compatible   Ggml   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/digitous/Alpacino30b 

Alpacino30b Benchmarks

ARC: 62.71 vs 96.7 (so35)-35.1%
HellaSwag: 85.04 vs 95.3 (gpt4)-10.8%
MMLU: 58.48 vs 88.3 (so35)-33.8%
TruthfulQA: 44.23 vs 59 (gpt4)-25%
WinoGrande: 79.79 vs 87.5 (gpt4)-8.8%
GSM8K: 15.77 vs 96.4 (so35)-83.6%
LLME Score: 0.11171
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Alpacino30b (digitous/Alpacino30b)

Alpacino30b Parameters and Internals

Model Type 
text generation, storytelling
Use Cases 
Applications:
Text-Generation-WebUI, KoboldAI
Primary Use Cases:
Text-Based Adventure Games
Limitations:
May output offensive text, May fabricate information
Considerations:
Better results using 'Storywriter' or 'Godlike' presets in Weber
Training Details 
Data Sources:
https://huggingface.co/datasets/yahma/alpaca-cleaned, https://huggingface.co/datasets/QingyiSi/Alpaca-CoT
Methodology:
LoRA (Low-Rank Adaptation) fine-tuning with Alpaca, CoT, and Storytelling datasets
Context Length:
2048
Model Architecture:
Triple model merge of Alpaca+CoT+Storytelling based on Llama30b
Input Output 
Performance Tips:
Better results with context tokens at 2048 and max generation tokens at 680 or more.
LLM NameAlpacino30b
Repository 🤗https://huggingface.co/digitous/Alpacino30b 
Model Size30b
Required VRAM64.1 GB
Updated2025-06-02
Maintainerdigitous
Model Typellama
Model Files  16.9 GB   24.4 GB   2.1 GB: 1-of-33   1.9 GB: 2-of-33   2.0 GB: 3-of-33   2.0 GB: 4-of-33   2.0 GB: 5-of-33   2.0 GB: 6-of-33   1.9 GB: 7-of-33   1.9 GB: 8-of-33   1.9 GB: 9-of-33   2.0 GB: 10-of-33   2.0 GB: 11-of-33   2.0 GB: 12-of-33   2.0 GB: 13-of-33   1.9 GB: 14-of-33   1.9 GB: 15-of-33   1.9 GB: 16-of-33   2.0 GB: 17-of-33   2.0 GB: 18-of-33   2.0 GB: 19-of-33   2.0 GB: 20-of-33   1.9 GB: 21-of-33   1.9 GB: 22-of-33   1.9 GB: 23-of-33   2.0 GB: 24-of-33   2.0 GB: 25-of-33   2.0 GB: 26-of-33   2.0 GB: 27-of-33   1.9 GB: 28-of-33   1.9 GB: 29-of-33   1.9 GB: 30-of-33   2.0 GB: 31-of-33   2.0 GB: 32-of-33   1.3 GB: 33-of-33
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Alpacino30b

Best Alternatives
Context / RAM
Downloads
Likes
Tamillama Tiny 30m2K / 0.1 GB15415
GPT4 X Alpasta 30B 4bit2K / 16.9 GB1868
Bluemoonrp 30B2K / 17.5 GB2024
GPT4 X Alpaca 30B 4bit2K / 16.9 GB13162
OpenAssistant Llama 30B 4bit2K / 16.9 GB1969
Tenebra 30B Alpha01 FP1616K / 65 GB18339
...nebra 30B Alpha01 EXL2 2 80bpw16K / 11.9 GB221
...nebra 30B Alpha01 EXL2 2 50bpw16K / 10.7 GB190
Tenebra 30B Alpha01 EXL2 3bpw16K / 12.7 GB140
Tenebra 30B Alpha01 3BIT16K / 12.9 GB190
Note: green Score (e.g. "73.2") means that the model is better than digitous/Alpacino30b.

Rank the Alpacino30b 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? 47796 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