8-bit Ar Autotrain compatible Cohere Cs De El En Es Fa Fr He Hi Id It Ja Ko Nl Pl Pt Region:us Ro Ru Safetensors Sharded Tensorflow Tr Uk Vi Zh
Aya 23 8B Quantized 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)
Aya 23 8B Quantized Parameters and Internals
| LLM Name | Aya 23 8B Quantized |
| Repository 🤗 | https://huggingface.co/jadechoghari/aya-23-8B-quantized |
| Model Size | 8b |
| Required VRAM | 8.1 GB |
| Updated | 2024-09-08 |
| Maintainer | jadechoghari |
| Model Type | cohere |
| Model Files | |
| Supported Languages | en fr de es it pt ja ko zh ar el fa pl id cs he hi nl ro ru tr uk vi |
| Model Architecture | CohereForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.42.4 |
| Vocabulary Size | 256000 |
| Torch Data Type | float32 |
Best Alternatives to Aya 23 8B Quantized
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ng On New Data For Testing Aya | 8K / 18.1 GB | 5 | 0 |
| Aya 23 8B 4bq | 8K / 5.7 GB | 5 | 0 |
| AYA 8B | 8K / 32.1 GB | 5 | 0 |
| Paya | 8K / 16 GB | 6 | 5 |
| U3reb | 8K / 5.7 GB | 0 | 0 |
| ...4ai Command R 08 2024 Bnb 4bit | 128K / 19.9 GB | 185 | 5 |
| ...ereForAI Aya 23 8B 8 0bpw EXL2 | 8K / 10.2 GB | 6 | 1 |
| ...ereForAI Aya 23 8B 6 0bpw EXL2 | 8K / 9.2 GB | 3 | 2 |
| Aya 23 8B 4bit | 8K / 4.5 GB | 4 | 2 |
| Aya 23 8B 8bit | 8K / 8.5 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than jadechoghari/aya-23-8B-quantized .
Rank the Aya 23 8B Quantized 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803