DCLM 7B Benchmarks
MMLU Pro: 23.45
GPQA: 8.72
MUSR: 7.31
BBH: 19.76
IFEval: 21.73 vs 88 (so35)-75.3%
MATH Lvl 5: 2.95
LLME Score: 0.44844
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)
DCLM 7B Parameters and Internals
| LLM Name | DCLM 7B |
| Repository 🤗 | https://huggingface.co/apple/DCLM-7B |
| Model Size | 7b |
| Required VRAM | 27.7 GB |
| Updated | 2024-09-08 |
| Maintainer | apple |
| Model Type | openlm |
| Model Files | |
| Model Architecture | OpenLMModel |
| License | apple-ascl |
| Transformers Version | 4.38.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float32 |
Rank the DCLM 7B 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803