LongMamba 16384 Bs128 Step400 Parameters and Internals
| LLM Name | LongMamba 16384 Bs128 Step400 |
| Repository | Open on 🤗 |
| Required VRAM | 11.6 GB |
| Updated | 2024-07-27 |
| Maintainer | PY007 |
| Model Files | |
| Model Architecture | AutoModel |
| Vocabulary Size | 50277 |
Best Alternatives to LongMamba 16384 Bs128 Step400
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Distil Longformer Base 4096 | 0.1 | 4K / 0.4 GB | 23 | 0 |
| Daedalus 1 | 0.2 | 1K / GB | 13 | 1 |
| Tiny Random Detr | — | 1K / 0.2 GB | 7 | 0 |
| Opengpt2 Pytorch Backward | — | 1K / 6 GB | 52 | 1 |
| Opengpt2 Pytorch Forward | — | 1K / 6 GB | 7 | 1 |
| Finsent Transformer | — | 0.5K / 0.4 GB | 7 | 1 |
| Coref Roberta Large | — | 0.5K / 1.4 GB | 6 | 1 |
| Simbert Chinese Tiny | 0.2 | 0.5K / 0 GB | 17 | 0 |
| Bert Chinese L 12 H 768 A 12 | 0.2 | 0.5K / 0.4 GB | 7 | 1 |
| Simbert Chinese Base | 0.2 | 0.5K / 0.4 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than PY007/LongMamba_16384_bs128_step400 .
Rank the LongMamba 16384 Bs128 Step400 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501