Add production model card artifact README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,7 @@ Custom PyTorch Transformer checkpoint trained on MeetingBank for meeting summari
|
|
| 32 |
|
| 33 |
## Architecture
|
| 34 |
|
| 35 |
-
.
|
|
| 60 |
|---|---|
|
| 61 |
| `meeting_model19.pt` | PyTorch checkpoint containing `model_state_dict`, optimizer states, epoch, and global step. |
|
| 62 |
| `config.json` | Training and architecture config converted from the Hydra run config. |
|
| 63 |
-
| `architecture.
|
| 64 |
| `tokenizer.json` | MeetingBank transcript tokenizer alias for source inputs. |
|
| 65 |
| `transcript_tokenizer.json` | Explicit MeetingBank transcript tokenizer. |
|
| 66 |
| `summary_tokenizer.json` | MeetingBank summary tokenizer for target text. |
|
|
|
|
| 32 |
|
| 33 |
## Architecture
|
| 34 |
|
| 35 |
+

|
| 36 |
|
| 37 |
Static architecture diagram generated from this run's `config.json`, including model width, depth, sequence dimensions, and attention-specific settings.
|
| 38 |
|
|
|
|
| 60 |
|---|---|
|
| 61 |
| `meeting_model19.pt` | PyTorch checkpoint containing `model_state_dict`, optimizer states, epoch, and global step. |
|
| 62 |
| `config.json` | Training and architecture config converted from the Hydra run config. |
|
| 63 |
+
| `architecture.png` | Architecture diagram generated from the saved model config, with block shapes and dimensions. |
|
| 64 |
| `tokenizer.json` | MeetingBank transcript tokenizer alias for source inputs. |
|
| 65 |
| `transcript_tokenizer.json` | Explicit MeetingBank transcript tokenizer. |
|
| 66 |
| `summary_tokenizer.json` | MeetingBank summary tokenizer for target text. |
|