mittagessen
commited on
Commit
•
8a85365
1
Parent(s):
0eedc64
Upload folder using huggingface_hub
Browse files- README.md +4 -0
- config.json +13 -0
- model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
---
|
3 |
+
|
4 |
+
These are the untrained weights of a ByteLlama model. More info can be found [here](https://github.com/mittagessen/bytellama).
|
config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"vocab_size": 259,
|
3 |
+
"num_layers": 30,
|
4 |
+
"num_heads": 9,
|
5 |
+
"num_kv_heads": 3,
|
6 |
+
"embed_dim": 576,
|
7 |
+
"max_seq_len": 384,
|
8 |
+
"intermediate_dim": 1536,
|
9 |
+
"attn_dropout": 0.0,
|
10 |
+
"norm_eps": 1e-5,
|
11 |
+
"rope_base": 10000,
|
12 |
+
"scale_factor": 32
|
13 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0668c376a9d1fe412e4b2a02bfffc70ed9d41d1b683d8a8b02848826e88dec9
|
3 |
+
size 567060720
|