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

VicUnlocked Alpaca 65B QLoRA Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  VicUnlocked Alpaca 65B QLoRA Fp16   URL Share it on

  810   

VicUnlocked Alpaca 65B QLoRA Fp16 is an open-source language model by TheBloke. Features: 65b LLM, VRAM: 130.4GB, Context: 2K, License: other, Quantized, HF Score: 62.6, LLM Explorer Score: 0.1, Arc: 65.6, HellaSwag: 85.2, MMLU: 63.1, TruthfulQA: 52.5, WinoGrande: 81.3, GSM8K: 27.8.

Dataset:gozfarb/sharegpt vicun...   Fp16   Llama   Lora   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TheBloke/VicUnlocked-alpaca-65B-QLoRA-fp16 

VicUnlocked Alpaca 65B QLoRA Fp16 Benchmarks

ARC: 65.61 vs 96.7 (so35)-32.2%
HellaSwag: 85.15 vs 95.3 (gpt4)-10.7%
MMLU: 63.13 vs 88.3 (so35)-28.5%
TruthfulQA: 52.47 vs 59 (gpt4)-11.1%
WinoGrande: 81.29 vs 87.5 (gpt4)-7.1%
GSM8K: 27.82 vs 96.4 (so35)-71.1%
LLME Score: 0.10261
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
VicUnlocked Alpaca 65B QLoRA Fp16 (TheBloke/VicUnlocked-alpaca-65B-QLoRA-fp16)
🌟 Advertise your project 🚀

VicUnlocked Alpaca 65B QLoRA Fp16 Parameters and Internals

Additional Notes 
This is a highly experimental LoRA model trained in the Alpaca format. It expects prompts in a specific format. Current upload is of checkpoint at step 1200 in training.
Training Details 
Data Sources:
gozfarb/ShareGPT_Vicuna_unfiltered
Methodology:
QLoRA
LLM NameVicUnlocked Alpaca 65B QLoRA Fp16
Repository 🤗https://huggingface.co/TheBloke/VicUnlocked-alpaca-65B-QLoRA-fp16 
Model Size65b
Required VRAM130.4 GB
Updated2026-03-31
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-14   9.7 GB: 2-of-14   9.7 GB: 3-of-14   9.7 GB: 4-of-14   9.7 GB: 5-of-14   9.7 GB: 6-of-14   9.7 GB: 7-of-14   9.7 GB: 8-of-14   9.7 GB: 9-of-14   9.7 GB: 10-of-14   9.7 GB: 11-of-14   9.7 GB: 12-of-14   9.7 GB: 13-of-14   4.1 GB: 14-of-14
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.30.0.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 VicUnlocked Alpaca 65B QLoRA Fp16

Best Alternatives
Context / RAM
Downloads
Likes
Robin 65B V2 Fp162K / 130.4 GB8423
Alpaca Elina 65B 4bit2K / 33.5 GB7837
...65B Gpt4 1.2 4bit 32g Actorder2K / 38.5 GB9130
....4.1 PI 8192 4bit 32g Actorder2K / 38.5 GB48
Enterredaas 65B 4bit 128g2K / 35.7 GB91
VicUnlocked Alpaca 65B 4bit2K / 35.7 GB76
Llama 65B 4bit2K / 34.7 GB42
LLaMA 65B 4bit 128g2K / 34.7 GB616
LLaMA 65B 4bit 32g2K / 38.5 GB710
Lite Oute 1 65M Instruct2K / 0.3 GB1712
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/VicUnlocked-alpaca-65B-QLoRA-fp16.

Rank the VicUnlocked Alpaca 65B QLoRA Fp16 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