Arxiv:1910.09700 Autotrain compatible Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow
Sn37 V3 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)
Sn37 V3 Parameters and Internals
| LLM Name | Sn37 V3 |
| Repository 🤗 | https://huggingface.co/luaqi/sn37_v3 |
| Model Size | 6.9b |
| Required VRAM | 13.8 GB |
| Updated | 2024-10-18 |
| Maintainer | luaqi |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.44.1 |
| Vocabulary Size | 100288 |
| Torch Data Type | bfloat16 |
Best Alternatives to Sn37 V3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bolna Lead Qualification | 16K / 13.8 GB | 3 | 3 |
| Fiufiu 71 | 4K / 13.8 GB | 673 | 0 |
| Fiufiu 87 | 4K / 13.8 GB | 521 | 0 |
| Sn37 V5 | 4K / 13.8 GB | 319 | 0 |
| Happymeow | 4K / 13.8 GB | 3167 | 0 |
| SambaLingo Thai Chat | 4K / 13.9 GB | 558 | 36 |
| Subnet9key16 | 4K / 13.8 GB | 3225 | 0 |
| Nine Aa | 4K / 13.8 GB | 306 | 0 |
| Jw2 | 4K / 13.8 GB | 454 | 0 |
| Sn9 Testing7 | 4K / 13.8 GB | 85 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than luaqi/sn37_v3 .
Rank the Sn37 V3 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803