Arxiv:2401.02731 Autotrain compatible Conversational Custom code Dataset:teknium/openhermes-2.5 En Endpoints compatible Moe Region:us Safetensors Sharded Sparsetral Tensorflow
Model Card on HF 🤗: https://huggingface.co/serpdotai/sparsetral-16x7B-v2
Sparsetral 16x7B V2 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)
Sparsetral 16x7B V2 Parameters and Internals
| LLM Name | Sparsetral 16x7B V2 |
| Repository 🤗 | https://huggingface.co/serpdotai/sparsetral-16x7B-v2 |
| Model Size | 9.4b |
| Required VRAM | 18.7 GB |
| Updated | 2024-12-26 |
| Maintainer | serpdotai |
| Model Type | sparsetral |
| Model Files | |
| Supported Languages | en |
| Model Architecture | modeling_sparsetral.MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Sparsetral 16x7B V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Sparsetral 16x7B V2 SPIN Iter1 | 32K / 18.7 GB | 21 | 13 |
| Sparsetral 16x7B V2 SPIN Iter0 | 32K / 18.7 GB | 15 | 8 |
| ...s Sparsetral Mistral 16x7b MoE | 32K / 18.7 GB | 11 | 4 |
Rank the Sparsetral 16x7B V2 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? 40248 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217