Autotrain compatible Base model:cohereforai/aya-23-... Base model:finetune:coherefora... Cohere Conversational Endpoints compatible Generated from trainer Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/ArmanAsq/AYA-8B
AYA 8B 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 8B Parameters and Internals
| LLM Name | AYA 8B |
| Repository 🤗 | https://huggingface.co/ArmanAsq/AYA-8B |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 32.1 GB |
| Updated | 2024-12-21 |
| Maintainer | ArmanAsq |
| Model Type | cohere |
| Model Files | |
| Model Architecture | CohereForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | CohereTokenizer |
| Padding Token | <PAD> |
| Vocabulary Size | 255029 |
| Torch Data Type | float32 |
Best Alternatives to AYA 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Aya Expanse 8B | 8K / 16 GB | 37388 | 307 |
| Aya 23 8B Quantized | 8K / 8.1 GB | 49 | 3 |
| ...ng On New Data For Testing Aya | 8K / 18.1 GB | 11 | 0 |
| Aya 23 8B 4bq | 8K / 5.7 GB | 13 | 0 |
| Paya | 8K / 16 GB | 5 | 5 |
| U3reb | 8K / 5.7 GB | 0 | 0 |
| Aya 23 8B 4bit | 8K / 4.5 GB | 20 | 2 |
| ...ereForAI Aya 23 8B 6 0bpw EXL2 | 8K / 9.2 GB | 12 | 2 |
| Aya 23 8B 8bit | 8K / 8.5 GB | 15 | 1 |
| ...reForAI Aya 23 8B 3 75bpw EXL2 | 8K / 6.7 GB | 10 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ArmanAsq/AYA-8B .
Rank the AYA 8B 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? 40013 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217