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

ORCA LLaMA 70B QLoRA GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  ORCA LLaMA 70B QLoRA GPTQ   URL Share it on

  36   
  Arxiv:2306.02707   Arxiv:2308.07317   4-bit   Autotrain compatible Base model:fangloveskari/orca ... Base model:quantized:fangloves...   En   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ 

ORCA LLaMA 70B QLoRA GPTQ Benchmarks

LLME Score: 0.13724
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ORCA LLaMA 70B QLoRA GPTQ (TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ)

ORCA LLaMA 70B QLoRA GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Limitations:
Potential outputs cannot be predicted in advance, and the model may produce inaccurate, biased, or objectionable responses.
Considerations:
Developers should perform safety testing and tuning tailored to their specific applications.
Training Details 
Data Sources:
Dolphin, Open-Platypus, OpenOrca
Methodology:
QLoRA(NF4) with mixed strategy: 100% Open-Platypus + ~1% Dolphin(GPT-4) + ~1% OpenOrca(GPT-4)
Hardware Used:
8xA100(80G) GPUs
Model Architecture:
Trained with flash_attention_2 and ORCA dataset support
LLM NameORCA LLaMA 70B QLoRA GPTQ
Repository 🤗https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ 
Model NameORCA LLaMA 70B QLoRA
Model Creatorfangloveskari
Base Model(s)  ORCA LLaMA 70B QLoRA   fangloveskari/ORCA_LLaMA_70B_QLoRA
Model Size70b
Required VRAM35.3 GB
Updated2024-12-21
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  35.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to ORCA LLaMA 70B QLoRA GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB22215
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB332
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB3544
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB82816
...erkrautLM 70B Instruct GPTQ 8B8K / 74.4 GB4131
...ama 3 Taiwan 70B Instruct GPTQ8K / 39.8 GB212
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB45319
...ta Llama 3 70B Instruct Marlin8K / 39.5 GB4136
...g Llama 3 70B Instruct GPTQ 8B8K / 74.4 GB31
...g Llama 3 70B Instruct GPTQ 4B8K / 39.8 GB60
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/ORCA_LLaMA_70B_QLoRA-GPTQ.

Rank the ORCA LLaMA 70B QLoRA GPTQ 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? 40013 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 v20241217
  Support LLM Explorer