Autotrain compatible Dataset:instruction Endpoints compatible Instruct Ko Llama Pytorch Region:us Sharded
Etri Ones Solar Benchmarks
ARC: 62.63 vs 96.7 (so35)-35.2%
HellaSwag: 84.31 vs 95.3 (gpt4)-11.5%
MMLU: 63.71 vs 88.3 (so35)-27.8%
TruthfulQA: 52.69 vs 59 (gpt4)-10.7%
WinoGrande: 81.93 vs 87.5 (gpt4)-6.4%
LLME Score: 0.2228
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)
Etri Ones Solar Parameters and Internals
| LLM Name | Etri Ones Solar |
| Repository 🤗 | https://huggingface.co/leejaymin/etri-ones-solar |
| Required VRAM | 42.9 GB |
| Updated | 2024-10-18 |
| Maintainer | leejaymin |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ko |
| Model Architecture | LlamaForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Etri Ones Solar
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| FATLLAMA 1.7T Instruct | 128K / 438.9 GB | 23 | 3 |
| Reverse Instruct | 32K / 27 GB | 8 | 3 |
| Law Chat | 4K / 27 GB | 1155 | 33 |
| Phi 3 Orpo V8.16 | 4K / 7.6 GB | 8 | 0 |
| Small Instruct | 4K / 2.9 GB | 4139 | 1 |
| Tinyllama Python | 4K / 2.2 GB | 7 | 1 |
| Model 007 Preview | 4K / 138 GB | 63 | 1 |
| Taiwan LLaMa V0.0 | 4K / 26 GB | 9 | 1 |
| Taiwan LLaMa V0.9 | 4K / 26 GB | 11 | 0 |
| Kolong Llama V0.1 | 2K / 13.7 GB | 4089 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than leejaymin/etri-ones-solar .
Rank the Etri Ones Solar 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