Push model using huggingface_hub.
Browse files- README.md +10 -0
- config.json +27 -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 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attn_bias": true,
|
| 3 |
+
"d_ff": 5464,
|
| 4 |
+
"d_model": 2048,
|
| 5 |
+
"dropout_p": 0.0,
|
| 6 |
+
"heads_per_group": 1,
|
| 7 |
+
"layer_group_size": 48,
|
| 8 |
+
"mlp_bias": false,
|
| 9 |
+
"norm_eps": 0.0005,
|
| 10 |
+
"norm_include_weight": false,
|
| 11 |
+
"num_groups": 32,
|
| 12 |
+
"num_heads": 32,
|
| 13 |
+
"num_layers": 48,
|
| 14 |
+
"num_output_patches": 1,
|
| 15 |
+
"num_variate_layers_per_group": 1,
|
| 16 |
+
"patch_size": 32,
|
| 17 |
+
"per_dim_scale": true,
|
| 18 |
+
"pre_norm": true,
|
| 19 |
+
"qk_dim": 64,
|
| 20 |
+
"qk_norm": false,
|
| 21 |
+
"qk_norm_include_weight": false,
|
| 22 |
+
"residual_attn_ratio": 5.136215466577748,
|
| 23 |
+
"residual_mult": 0.75,
|
| 24 |
+
"use_xpos": true,
|
| 25 |
+
"v_dim": 64,
|
| 26 |
+
"variate_layer_first": false
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fbc02988b580dcd0b6d2c56df010eca3b233cf9ea91454e5de3ec0f11240188
|
| 3 |
+
size 9817176960
|