| model_info: | |
| name: anemll-Llama-3.1-Nemotron-Nano-8B-v1-ctx512 | |
| version: 0.3.0 | |
| description: | | |
| Demonstarates running Llama-3.1-Nemotron-Nano-8B-v1 on Apple Neural Engine | |
| Context length: 512 | |
| Batch size: 64 | |
| Chunks: 16 | |
| license: MIT | |
| author: Anemll | |
| framework: Core ML | |
| language: Python | |
| parameters: | |
| context_length: 512 | |
| batch_size: 64 | |
| lut_embeddings: none | |
| lut_ffn: none | |
| lut_lmhead: none | |
| num_chunks: 16 | |
| model_prefix: nemo_ | |
| embeddings: nemo__embeddings.mlmodelc | |
| lm_head: nemo__lm_head.mlmodelc | |
| ffn: nemo__FFN_PF.mlmodelc | |