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

LLaMA 2 Wizard 70B QLoRA by v2ray

 »  All LLMs  »  v2ray  »  LLaMA 2 Wizard 70B QLoRA   URL Share it on

  0   
  Adapter   Conversational Dataset:wizardlm/wizardlm evol...   En   Finetuned   Instruct   Lora   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/v2ray/LLaMA-2-Wizard-70B-QLoRA 

LLaMA 2 Wizard 70B QLoRA Benchmarks

ARC: 67.58 vs 96.7 (so35)-30.1%
HellaSwag: 87.52 vs 95.3 (gpt4)-8.2%
MMLU: 69.11 vs 88.3 (so35)-21.7%
TruthfulQA: 61.79 vs 59 (gpt4)4.7%
WinoGrande: 82.32 vs 87.5 (gpt4)-5.9%
GSM8K: 30.48 vs 96.4 (so35)-68.4%
LLME Score: 0.1115
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaMA 2 Wizard 70B QLoRA (v2ray/LLaMA-2-Wizard-70B-QLoRA)
🌟 Advertise your project 🚀

LLaMA 2 Wizard 70B QLoRA Parameters and Internals

Model Type 
conversational
Supported Languages 
en (proficient)
Training Details 
Data Sources:
WizardLM/WizardLM_evol_instruct_V2_196k
Methodology:
Fine-tuned on WizardLM/WizardLM_evol_instruct_V2_196k dataset
LLM NameLLaMA 2 Wizard 70B QLoRA
Repository 🤗https://huggingface.co/v2ray/LLaMA-2-Wizard-70B-QLoRA 
Model Size70b
Required VRAM1.7 GB
Updated2025-09-23
Maintainerv2ray
Instruction-BasedYes
Model Files  1.7 GB   1.7 GB
Supported Languagesen
Model ArchitectureAdapter
Licensellama2
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|q_proj|down_proj|v_proj|up_proj|o_proj|k_proj
LoRA Alpha128
LoRA Dropout0.05
R Param64

Quantized Models of the LLaMA 2 Wizard 70B QLoRA

Model
Likes
Downloads
VRAM
Llama 3 70B Fp164324141 GB

Best Alternatives to LLaMA 2 Wizard 70B QLoRA

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.1 70B Abliterated Lora0K / 1.7 GB267573
Llama 3 70B Instruct Spider0K / 141.9 GB60
Llama3v10K / 0.1 GB60
Saiga2 70b Lora0K / 0.3 GB014
Llama 2 70B Instruct V0.10K / 1.1 GB6814
Note: green Score (e.g. "73.2") means that the model is better than v2ray/LLaMA-2-Wizard-70B-QLoRA.

Rank the LLaMA 2 Wizard 70B QLoRA 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? 51611 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 v20241124
  Support LLM Explorer