Merged Model Abliterated Autotrain compatible Base model:aiaf/pretrained-scp... Base model:apider/llama-3.2-1b... Base model:novaciano/baphomet Base model:qingy2024/benchmaxx... Conversational En Endpoints compatible Es Instruct Llama Llama3.3 Model-index Not-for-all-audiences Region:us Safetensors Sharded Tensorflow Uncensored
Model Card on HF 🤗: https://huggingface.co/Novaciano/Cerberus-3.2-1B
Cerberus 3.2 1B Benchmarks
MMLU Pro: 7.37
GPQA: 1.12
MUSR: 0.94
BBH: 16.97
IFEval: 50.17 vs 88 (so35)-43%
MATH Lvl 5: 5.82
LLME Score: 0.29872
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)
Cerberus 3.2 1B Parameters and Internals
| LLM Name | Cerberus 3.2 1B |
| Repository 🤗 | https://huggingface.co/Novaciano/Cerberus-3.2-1B |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 1b |
| Required VRAM | 2.5 GB |
| Updated | 2025-03-18 |
| Maintainer | Novaciano |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en es |
| Model Architecture | LlamaForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Cerberus 3.2 1B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 2695119 | 823 |
| Llama 3.2 1B Instruct | 128K / 2.5 GB | 210645 | 67 |
| ...enchmaxx Llama 3.2 1B Instruct | 128K / 0 GB | 411 | 2 |
| Goppa LogiLlama | 128K / 4.9 GB | 767 | 11 |
| Llama 3.2 1b SunOrca V1 | 128K / 3 GB | 166 | 0 |
| ... 6 1B Instruct Abliterated LPL | 128K / 2.5 GB | 191 | 0 |
| Lancer 1 1B Instruct | 128K / 2.5 GB | 182 | 1 |
| Llama 3.2 1b OrcaSun V1 | 128K / 3 GB | 26 | 0 |
| Mini Think Base 1B | 128K / 2.5 GB | 79 | 1 |
| BunderMaxx 1010 | 128K / 2.5 GB | 14 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Novaciano/Cerberus-3.2-1B .
Rank the Cerberus 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! 🌟
What open-source LLMs or SLMs are you in search of? 45231 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227