Model Card on HF 🤗: https://huggingface.co/anas-awadalla/mpt-7b
Mpt 7B Benchmarks
ARC: 47.7 vs 96.7 (so35)-50.7%
HellaSwag: 77.57 vs 95.3 (gpt4)-18.6%
MMLU: 30.8 vs 88.3 (so35)-65.1%
TruthfulQA: 33.44 vs 59 (gpt4)-43.3%
WinoGrande: 72.14 vs 87.5 (gpt4)-17.6%
GSM8K: 4.02 vs 96.4 (so35)-95.8%
LLME Score: 0.17553
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)
Mpt 7B Parameters and Internals
| LLM Name | Mpt 7B |
| Repository 🤗 | https://huggingface.co/anas-awadalla/mpt-7b |
| Model Size | 7b |
| Required VRAM | 26.5 GB |
| Updated | 2025-02-22 |
| Maintainer | anas-awadalla |
| Model Type | mpt |
| Model Files | |
| Model Architecture | MPTForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.28.0 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float32 |
Best Alternatives to Mpt 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mpt 7B Chat | 0K / 13.3 GB | 95245 | 512 |
| Mpt 7B | 0K / 13.3 GB | 31576 | 1165 |
| Mpt 7B Instruct | 0K / 13.3 GB | 15434 | 469 |
| Mpt 7B Storywriter | 0K / 13.3 GB | 3114 | 830 |
| Mpt 7B Int8 Ov | 0K / 0 GB | 27 | 0 |
| Shears Mpt 7B 50 Base | 0K / 13.3 GB | 81 | 2 |
| Sea Lion 7B Instruct | 0K / 15 GB | 357 | 23 |
| Mpt 7B 8K | 0K / 13.3 GB | 2493 | 26 |
| Mpt 7B 8K Chat | 0K / 13.3 GB | 2150 | 40 |
| Mpt 7B 8K Instruct | 0K / 13.3 GB | 2057 | 26 |
Note: green Score (e.g. "73.2") means that the model is better than anas-awadalla/mpt-7b .
Rank the Mpt 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227