Arxiv:1910.09700 Autotrain compatible Endpoints compatible Mamba Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ArthurZ/mamba-2.8b
Mamba 2.8B 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)
Mamba 2.8B Parameters and Internals
| LLM Name | Mamba 2.8B |
| Repository 🤗 | https://huggingface.co/ArthurZ/mamba-2.8b |
| Model Size | 2.8b |
| Required VRAM | 5.6 GB |
| Updated | 2025-02-22 |
| Maintainer | ArthurZ |
| Model Type | mamba |
| Model Files | |
| Model Architecture | MambaForCausalLM |
| Transformers Version | 4.38.0.dev0 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50280 |
| Torch Data Type | float16 |
Best Alternatives to Mamba 2.8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mamba 2.8B Hf | 0K / 11.1 GB | 4783 | 98 |
| Clinicalmamba 2.8B Hf | 0K / 11.1 GB | 74 | 2 |
| Mamba 2.8B Ultrachat Hf | 0K / 11.1 GB | 20 | 1 |
| Mamba 2.8B Slimpj Hf | 0K / 11.1 GB | 22 | 0 |
| Mamba 2.8B Zephyr Hf | 0K / 11.1 GB | 19 | 0 |
| Mamba 2.8B Slimpj | 0K / 5.6 GB | 82 | 0 |
| Mamba Ko 2.8B | 0K / 5.8 GB | 43 | 18 |
| Mamba 2.8B Hf GGUF | 0K / 1.4 GB | 16 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ArthurZ/mamba-2.8b .
Rank the Mamba 2.8B 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