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

Vicuna 13B V1.5 PL Lora Unload by Aspik101

 »  All LLMs  »  Aspik101  »  Vicuna 13B V1.5 PL Lora Unload   URL Share it on

  100   

Vicuna 13B V1.5 PL Lora Unload is an open-source language model by Aspik101. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: other, Instruction-Based, LLM Explorer Score: 0.11, Arc: 56.9, HellaSwag: 81.2, MMLU: 56.1, GSM8K: 12.3.

Dataset:lajonbot/alpaca-dolly-...   Endpoints compatible   Facebook   Instruct   Llama   Llama2   Lora   Meta   Pl   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Aspik101/vicuna-13b-v1.5-PL-lora_unload 

Vicuna 13B V1.5 PL Lora Unload Benchmarks

ARC: 56.91 vs 96.7 (so35)-41.1%
HellaSwag: 81.22 vs 95.3 (gpt4)-14.8%
MMLU: 56.06 vs 88.3 (so35)-36.5%
GSM8K: 12.28 vs 96.4 (so35)-87.3%
LLME Score: 0.10762
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Vicuna 13B V1.5 PL Lora Unload (Aspik101/vicuna-13b-v1.5-PL-lora_unload)
🌟 Advertise your project 🚀

Vicuna 13B V1.5 PL Lora Unload Parameters and Internals

Model Type 
llama-2
LLM NameVicuna 13B V1.5 PL Lora Unload
Repository 🤗https://huggingface.co/Aspik101/vicuna-13b-v1.5-PL-lora_unload 
Model Size13b
Required VRAM26 GB
Updated2026-06-25
MaintainerAspik101
Model Typellama-2
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagespl
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
LoRA ModelYes
Torch Data Typefloat16

Best Alternatives to Vicuna 13B V1.5 PL Lora Unload

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven V2 13B16K / 26 GB85471
CodeLlama 13B Instruct Hf16K / 26 GB2286160
CodeLlama 13B MORepair16K / 26 GB112
CodeLlama 13B Instruct Hf16K / 26 GB286128
TableLLM 13B16K / 26 GB4432
NexusRaven 13B16K / 26 GB14105
Panda Coder 13B16K / 26 GB1914
... Llama 2 13B Instruct Text2sql16K / 26 GB2628
Gen Sim16K / 0.3 GB83
Llama 3 13B Instruct Ft8K / 26.1 GB62
Note: green Score (e.g. "73.2") means that the model is better than Aspik101/vicuna-13b-v1.5-PL-lora_unload.

Rank the Vicuna 13B V1.5 PL Lora Unload 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? 54677 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