Makandal Pre Trained is an open-source language model by jsbeaudry. Features: 111.9m LLM, VRAM: 0.4GB, License: mit, LLM Explorer Score: 0.19.
Base model:finetune:jsbeaudry/... Base model:jsbeaudry/makandal-... Creole Endpoints compatible Gpt2 Haitian Ht Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/jsbeaudry/makandal-pre-trained
Makandal Pre Trained Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Makandal Pre Trained Parameters and Internals
| LLM Name | Makandal Pre Trained |
| Repository 🤗 | https://huggingface.co/jsbeaudry/makandal-pre-trained |
| Base Model(s) | |
| Model Size | 111.9m |
| Required VRAM | 0.4 GB |
| Updated | 2026-05-25 |
| Maintainer | jsbeaudry |
| Model Type | gpt2 |
| Model Files | |
| Supported Languages | ht |
| Model Architecture | GPT2LMHeadModel |
| License | mit |
| Transformers Version | 4.52.4 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 33977 |
| Torch Data Type | float32 |
| Activation Function | gelu_new |
| Errors | replace |
Rank the Makandal Pre Trained 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! 🌟
What open-source LLMs or SLMs are you in search of? 54384 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a