Model Card on HF 🤗: https://huggingface.co/vonjack/MobileLLM-125M-HF
MobileLLM 125M HF Benchmarks
MMLU Pro: 1.82
GPQA: 1.34
MUSR: 5.11
BBH: 3.15
IFEval: 21.07 vs 88 (so35)-76.1%
MATH Lvl 5: 0.91
LLME Score: 0.25184
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)
MobileLLM 125M HF Parameters and Internals
| LLM Name | MobileLLM 125M HF |
| Repository 🤗 | https://huggingface.co/vonjack/MobileLLM-125M-HF |
| Model Size | 125m |
| Required VRAM | 0.2 GB |
| Updated | 2025-02-23 |
| Maintainer | vonjack |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.31.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Rank the MobileLLM 125M HF 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? 43515 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227