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

Regex AI Llama 3.2 1B by mishl

 »  All LLMs  »  mishl  »  Regex AI Llama 3.2 1B   URL Share it on

  128   
  4bit Base model:meta-llama/llama-3.... Base model:quantized:meta-llam...   Code generation   Conversational   Dataset:phongo/regex   En   Endpoints compatible   Gguf   Instruct   Llama   Pytorch   Quantized   Regex   Region:us
Model Card on HF 🤗: https://huggingface.co/mishl/Regex-AI-Llama-3.2-1B 

Regex AI Llama 3.2 1B Benchmarks

LLME Score: 0.22572
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Regex AI Llama 3.2 1B (mishl/Regex-AI-Llama-3.2-1B)

Regex AI Llama 3.2 1B Parameters and Internals

LLM NameRegex AI Llama 3.2 1B
Repository 🤗https://huggingface.co/mishl/Regex-AI-Llama-3.2-1B 
Base Model(s)  meta-llama/Llama-3.2-1B-Instruct   meta-llama/Llama-3.2-1B-Instruct
Model Size1b
Required VRAM0.8 GB
Updated2025-02-22
Maintainermishl
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB   2.5 GB   0.8 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|4bit
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Regex AI Llama 3.2 1B

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 SUN 1B Chat128K / 1.6 GB1601
Llama 3.2 1B Instruct 4bit128K / 0.7 GB261032413
...2 1B Instruct Unsloth Bnb 4bit128K / 1.1 GB665411
Llama 3.2 1B Instruct Bnb 4bit128K / 1 GB5549514
Llama3.2 1b 2025 Uncensored V2128K / 1.3 GB12534
Llama Deepsync 1B128K / 2.5 GB1989
Orca Mini V9 5 1B Instruct128K / 2.5 GB874
Bunder 1B V0.1128K / 2.5 GB630
... Mini V9 5 1B Instruct Preview128K / 2.5 GB782
Orca Mini V9 1 1B Instruct128K / 2.5 GB893
Note: green Score (e.g. "73.2") means that the model is better than mishl/Regex-AI-Llama-3.2-1B.

Rank the Regex AI Llama 3.2 1B 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? 43470 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