Stentor 30M Instruct Heretic Safety Defiltered is an open-source language model by MihaiPopa-1. Features: 30m LLM, VRAM: 0.1GB, Context: 0.5K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25.
30m-parameters Abliterated Base model:adapter:stentorlabs... Base model:stentorlabs/stentor... Beavertails Chat Conversational Dataset:amazonscience/falserej... Dataset:databricks/databricks-... Dataset:pku-alignment/beaverta... Decensored Defiltered Dolly Edge-deployment Efficient En Endpoints compatible Heretic Instruct Instruction-following Llama Lora Model-index Peft Region:us Safetensors Safety-defiltered Safety-tuning Small-language-model Tiny-model Uncensored
Model Card on HF 🤗: https://huggingface.co/MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered
Stentor 30M Instruct Heretic Safety Defiltered 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)
Stentor 30M Instruct Heretic Safety Defiltered Parameters and Internals
| LLM Name | Stentor 30M Instruct Heretic Safety Defiltered |
| Repository 🤗 | https://huggingface.co/MihaiPopa-1/Stentor-30M-Instruct-heretic-safety-defiltered |
| Base Model(s) | |
| Model Size | 30m |
| Required VRAM | 0.1 GB |
| Updated | 2026-04-09 |
| Maintainer | MihaiPopa-1 |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 512 |
| Model Max Length | 512 |
| Transformers Version | 5.2.0 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | </s> |
| Vocabulary Size | 32768 |
Best Alternatives to Stentor 30M Instruct Heretic Safety Defiltered
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ct 2048 Open Platypus 100steps | 2K / 65.2 GB | 1749 | 0 |
| Llama 30B Instruct 2048 | 2K / 65.2 GB | 810 | 102 |
| ...azarus Instruct PL Lora Unload | 2K / 65.2 GB | 749 | 0 |
| Llama 30B Instruct | 2K / 65.2 GB | 1132 | 23 |
| ...B 2048 Instruct PL Lora Unload | 2K / 65.2 GB | 791 | 1 |
| ...lama 30B Instruct 2048 PL Lora | 2K / 65.2 GB | 1018 | 0 |
| ...pt Research Oig Oasst1 512 30B | 2K / 81.1 GB | 1866 | 3 |
| H2ogpt Oasst1 512 30B HF | 2K / 65 GB | 1326 | 2 |
| Open Instruct Human Mix 30B | 2K / 130.5 GB | 18 | 1 |
| Manticore 30B Chat Pyg Alpha | 0K / 65.2 GB | 1171 | 13 |
Rank the Stentor 30M Instruct Heretic Safety Defiltered 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? 52687 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