Arxiv:2312.15166 Autotrain compatible Code Conversational Dataset:intel/orca dpo pairs En Endpoints compatible Instruct Mixtral Model-index Moe Region:us Safetensors Sharded Tensorflow
Orca SOLAR 4x10.7B Benchmarks
ARC: 68.52 vs 96.7 (so35)-29.1%
HellaSwag: 86.78 vs 95.3 (gpt4)-8.9%
MMLU: 67.03 vs 88.3 (so35)-24.1%
TruthfulQA: 64.54 vs 59 (gpt4)9.4%
WinoGrande: 83.9 vs 87.5 (gpt4)-4.1%
GSM8K: 68.23 vs 96.4 (so35)-29.2%
LLME Score: 0.2025
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)
Orca SOLAR 4x10.7B Parameters and Internals
| LLM Name | Orca SOLAR 4x10.7B |
| Repository 🤗 | https://huggingface.co/macadeliccc/Orca-SOLAR-4x10.7b |
| Model Size | 36.1b |
| Required VRAM | 72.3 GB |
| Updated | 2024-10-18 |
| Maintainer | macadeliccc |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Orca SOLAR 4x10.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mixolar 4x7b | 4K / 72.3 GB | 3185 | 3 |
| SOLAR Polyglot 4x10.7B | 4K / 72.3 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than macadeliccc/Orca-SOLAR-4x10.7b .
Rank the Orca SOLAR 4x10.7B 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