Upload 3 files
Browse files- config.json +15 -0
- model.pt +3 -0
- tokenizer.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 1734,
|
| 3 |
+
"d_model": 512,
|
| 4 |
+
"n_heads": 8,
|
| 5 |
+
"n_layers": 10,
|
| 6 |
+
"n_shared_layers": 2,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"max_seq_len": 192,
|
| 9 |
+
"dropout": 0.05,
|
| 10 |
+
"lora_rank": 16,
|
| 11 |
+
"use_thinking_tokens": true,
|
| 12 |
+
"n_thinking_steps": 4,
|
| 13 |
+
"rope_base": 10000,
|
| 14 |
+
"weight_tying": true
|
| 15 |
+
}
|
model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:accf5723e9f93f36e235a562df1da79862d7fc0db735808d93265bde49548489
|
| 3 |
+
size 12221767
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|