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

Airoboros C34b 2.2.1 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Airoboros C34b 2.2.1 GPTQ   URL Share it on

  41   
  4-bit   Autotrain compatible Base model:jondurbin/airoboros... Base model:quantized:jondurbin... Dataset:jondurbin/airoboros-2....   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GPTQ 

Airoboros C34b 2.2.1 GPTQ Benchmarks

LLME Score: 0.13448
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Airoboros C34b 2.2.1 GPTQ (TheBloke/airoboros-c34b-2.2.1-GPTQ)

Airoboros C34b 2.2.1 GPTQ Parameters and Internals

Model Type 
llama
Additional Notes 
This model focuses heavily on instruction following rather than casual chat or roleplay.
Training Details 
Data Sources:
jondurbin/airoboros-2.2.1
Methodology:
Using mostly synthetic data generated by Airoboros. This is a minor 'fix' branch of airoboros-c34b-2.2 with updates like re-generated writing responses, longer contextual blocks, removal of 'rp' data, less aggressive de-censoring, and trained for 5 epochs instead of 3.
Input Output 
Input Format:
A chat.\nUSER: {prompt}\nASSISTANT: \n
Performance Tips:
For closed-context instructions, it is recommended to use explicit delimiters to help the model understand where to find responses.
LLM NameAiroboros C34b 2.2.1 GPTQ
Repository 🤗https://huggingface.co/TheBloke/airoboros-c34b-2.2.1-GPTQ 
Model NameAiroboros C34B 2.2.1
Model CreatorJon Durbin
Base Model(s)  jondurbin/airoboros-c34b-2.2.1   jondurbin/airoboros-c34b-2.2.1
Model Size4.7b
Required VRAM17.7 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  17.7 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.33.2
Tokenizer ClassCodeLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Airoboros C34b 2.2.1 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Airoboros C34B 3.1.2 GPTQ16K / 17.7 GB131
Airoboros C34B 2.2 GPTQ16K / 17.7 GB231
Airoboros C34B 2.1 GPTQ16K / 17.7 GB3612
Llama3.1 Merged128K / 5.8 GB750
EPFL TA Meister 4bit8K / 5.8 GB950
Book 4bitV58K / 5.8 GB770
Book 4bit8K / 5.8 GB50
Llama3 Ko 4bit8K / 5.8 GB770
Tenebra PreAlpha 128g 4BIT2K / 17.6 GB90
Hola8K / 5.8 GB770
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/airoboros-c34b-2.2.1-GPTQ.

Rank the Airoboros C34b 2.2.1 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? 42577 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