Model Card on HF 🤗: https://huggingface.co/PleIAs/Pleias-Nano
Pleias Nano 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)
Pleias Nano Parameters and Internals
| LLM Name | Pleias Nano |
| Repository 🤗 | https://huggingface.co/PleIAs/Pleias-Nano |
| Model Size | 1.2b |
| Required VRAM | 2.4 GB |
| Updated | 2025-02-05 |
| Maintainer | PleIAs |
| Model Type | llama |
| Model Files | |
| Supported Languages | en fr de es it nl la pt |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.46.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 65536 |
| Torch Data Type | bfloat16 |
Best Alternatives to Pleias Nano
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama Express.1 Merged | 128K / 2.5 GB | 57 | 7 |
| Query Templatizer Full | 128K / 2.5 GB | 104 | 0 |
| Lamma Operons | 128K / 4.9 GB | 10 | 0 |
| Pleias 1.2B Preview | 2K / 2.4 GB | 191 | 15 |
| TinyLlama Czech Poet | 2K / 4.9 GB | 4 | 1 |
| Llama2 1.2B Init | 2K / 2.4 GB | 116 | 0 |
| CSTinyLlama 1.2B | 2K / 4.9 GB | 348 | 9 |
| Tini Llama Full | 2K / 4.9 GB | 52 | 0 |
| Cutie GPTQ | 4K / 4.2 GB | 16 | 0 |
| Cutie AWQ | 4K / 4.2 GB | 7 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than PleIAs/Pleias-Nano .
Rank the Pleias Nano 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227