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

Velara GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Velara GPTQ   URL Share it on

  6   
  4-bit   Autotrain compatible   Base model:delcos/velara Base model:quantized:delcos/ve...   Conversational   En   Gptq   Llama2   Mistral   Quantized   Region:us   Safetensors   Starling
Model Card on HF 🤗: https://huggingface.co/TheBloke/Velara-GPTQ 

Velara GPTQ Benchmarks

LLME Score: 0.12511
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Velara GPTQ (TheBloke/Velara-GPTQ)
🌟 Advertise your project 🚀

Velara GPTQ Parameters and Internals

Model Type 
mistral, text-generation
Use Cases 
Limitations:
known limitations in prompt deviations and context retention
Additional Notes 
Velara is designed to enhance conversational realism by adhering more strictly to context and character while avoiding generic responses.
Supported Languages 
en (fluent)
Input Output 
Input Format:
### Instruction: {prompt} ### Response:
Accepted Modalities:
text
Output Format:
text
LLM NameVelara GPTQ
Repository 🤗https://huggingface.co/TheBloke/Velara-GPTQ 
Model NameVelara
Model CreatorDevon M
Base Model(s)  Velara   Delcos/Velara
Model Size1.8b
Required VRAM6.3 GB
Updated2025-09-21
MaintainerTheBloke
Model Typemistral
Model Files  6.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-nd-4.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<|im_end|>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Velara GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
H2o Danube2 1.8B Chat MLX 4bit8K / 1.1 GB41
Velara AWQ32K / 6.3 GB60
H2o Danube 1.8B Chat16K / 3.7 GB10454
H2o Danube 1.8B Base16K / 3.7 GB10943
Cypher Mini 1.8B16K / 3.7 GB62
H2o Danube 1.8B Sft16K / 3.7 GB9211
PixieZehirNano16K / 3.7 GB100
Cypher CoT 1.8B16K / 3.7 GB61
...1.8B Chat Sft Merge Fourier V116K / 7.3 GB41
H2o Danube2 1.8B Chat8K / 3.7 GB51861
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Velara-GPTQ.

Rank the Velara 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? 51507 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