Push model using huggingface_hub.
Browse files- README.md +9 -0
- config.json +14 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- Library: [More Information Needed]
|
| 9 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"bias": false,
|
| 4 |
+
"d_model": 1536,
|
| 5 |
+
"dff": null,
|
| 6 |
+
"dropout_rate": 0.0,
|
| 7 |
+
"max_block_size": 1024,
|
| 8 |
+
"n_heads": 24,
|
| 9 |
+
"n_layers": 24,
|
| 10 |
+
"norm_first": true,
|
| 11 |
+
"pos_enc_type": "RoPE",
|
| 12 |
+
"use_flash_attention": true,
|
| 13 |
+
"vocab_size": 50304
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1de34e79ffb576f8c7bfbe5fa658186bcdbd4be22086f0796f40d73659c43a8f
|
| 3 |
+
size 3027605256
|