| model_info: | |
| name: anemll-Meta-Llama-3.2-3B-ctx1024 | |
| version: 0.2.0 | |
| description: | | |
| Demonstarates running Meta-Llama-3.2-3B on Apple Neural Engine | |
| Context length: 1024 | |
| Batch size: 64 | |
| Chunks: 4 | |
| license: MIT | |
| author: Anemll | |
| framework: Core ML | |
| language: Python | |
| parameters: | |
| context_length: 1024 | |
| batch_size: 64 | |
| lut_embeddings: 8 | |
| lut_ffn: 8 | |
| lut_lmhead: 8 | |
| num_chunks: 4 | |
| model_prefix: llama | |
| embeddings: llama_embeddings_lut8.mlmodelc | |
| lm_head: llama_lm_head_lut8.mlmodelc | |
| ffn: llama_FFN_PF_lut8.mlmodelc | |