Dhara 250M Ar Base is an open-source language model by codelion. Features: 50b LLM, VRAM: 0.5GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.25.
Arxiv:2407.20311 Canon-layers Custom code Dataset:allenai/dolma3 longmin... Dataset:codelion/sutra-10b Dhara ar En Language-model Region:us Rope-yarn Safetensors Yarn
Model Card on HF 🤗: https://huggingface.co/codelion/dhara-250m-ar-base
Dhara 250M Ar Base 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)
Dhara 250M Ar Base Parameters and Internals
| LLM Name | Dhara 250M Ar Base |
| Repository 🤗 | https://huggingface.co/codelion/dhara-250m-ar-base |
| Model Size | 50b |
| Required VRAM | 0.5 GB |
| Updated | 2026-05-27 |
| Maintainer | codelion |
| Model Type | dhara_ar |
| Model Files | |
| Supported Languages | en |
| Model Architecture | DharaARForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 5.2.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|pad|> |
| Vocabulary Size | 49152 |
Rank the Dhara 250M Ar Base 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? 54454 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