NOTICE
| 1 | Modifications: handy-computer converted |
| 2 | https://huggingface.co/nvidia/canary-1b-v2 at commit 87bc526 to GGUF for |
| 3 | transcribe.cpp (https://github.com/handy-computer/transcribe.cpp). Conversion |
| 4 | repackages the weights, renaming and re-laying-out tensors; the quantized |
| 5 | files (Q8_0, Q6_K, Q5_K_M, Q4_K_M) also store them at reduced numeric |
| 6 | precision. The weights were not retrained or fine-tuned. |
| 7 | |