Fix config: lm_head is NOT tied (checkpoint stores two distinct 65x128 tensors; model.py never ties). Set tie_word_embeddings=false to match the artifact.
Browse files- config.json +14 -0
config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CharGPT"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "charlm",
|
| 6 |
+
"vocab_size": 65,
|
| 7 |
+
"block_size": 128,
|
| 8 |
+
"n_layer": 6,
|
| 9 |
+
"n_head": 4,
|
| 10 |
+
"n_embd": 128,
|
| 11 |
+
"tie_word_embeddings": false,
|
| 12 |
+
"n_params": 1216000,
|
| 13 |
+
"torch_dtype": "float32"
|
| 14 |
+
}
|