Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +22 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- model_hub_mixin
|
| 4 |
+
- pytorch_model_hub_mixin
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 8 |
+
- Code: [More Information Needed]
|
| 9 |
+
- Paper: [More Information Needed]
|
| 10 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cfg": {
|
| 3 |
+
"batch": 64,
|
| 4 |
+
"context_length": 1024,
|
| 5 |
+
"cycle": 200,
|
| 6 |
+
"ddp_local_rank": 0,
|
| 7 |
+
"drop_rate": 0.1,
|
| 8 |
+
"emb_dim": 768,
|
| 9 |
+
"lr": 0.0004,
|
| 10 |
+
"n_heads": 12,
|
| 11 |
+
"n_layers": 12,
|
| 12 |
+
"num_epoch": 1,
|
| 13 |
+
"tok_per_batch": 524288,
|
| 14 |
+
"total_tok": 9898595200,
|
| 15 |
+
"val_ratio": 0.1,
|
| 16 |
+
"vocab_size": 50304,
|
| 17 |
+
"warmup_ratio": 0.00125,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"world_size": 1
|
| 20 |
+
},
|
| 21 |
+
"tied": true
|
| 22 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b89b59de67e58acbd0b6cb62d7b72dd37134e34ccf872b5ccdb4624ca3d37c8
|
| 3 |
+
size 497768520
|