Push model using huggingface_hub.
Browse files- README.md +9 -0
- config.json +24 -0
- model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- pytorch_model_hub_mixin
|
4 |
+
- model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using ****:
|
8 |
+
- Repo: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bias": false,
|
3 |
+
"capacity_factor": 0.12,
|
4 |
+
"d_model": 1024,
|
5 |
+
"dropout": 0.2,
|
6 |
+
"ffn": "swiglu",
|
7 |
+
"hidden_dim": 4096,
|
8 |
+
"mixture_of_depth": true,
|
9 |
+
"mixture_of_expert": false,
|
10 |
+
"model_type": {
|
11 |
+
"mixture_of_depth": true,
|
12 |
+
"name": "mixture of depth"
|
13 |
+
},
|
14 |
+
"moe_num_experts": 4,
|
15 |
+
"moe_num_experts_per_tok": 2,
|
16 |
+
"multiple_of": 4,
|
17 |
+
"num_heads": 16,
|
18 |
+
"num_kv_heads": 0,
|
19 |
+
"num_layers": 16,
|
20 |
+
"seq_len": 512,
|
21 |
+
"vocab_size": 50257,
|
22 |
+
"weight_tying": true,
|
23 |
+
"window_size": 128
|
24 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a31bfebb9bca10b5ee49c499aa9f8e74bb81f7df94345a7043a72cdad4a90386
|
3 |
+
size 1281064680
|