Training in progress, epoch 0
Browse files- config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"max_position_embeddings": 32768,
|
| 18 |
"model_type": "gemma3_text",
|
| 19 |
"num_attention_heads": 4,
|
| 20 |
-
"num_hidden_layers":
|
| 21 |
"num_key_value_heads": 1,
|
| 22 |
"pad_token_id": 0,
|
| 23 |
"query_pre_attn_scalar": 256,
|
|
|
|
| 17 |
"max_position_embeddings": 32768,
|
| 18 |
"model_type": "gemma3_text",
|
| 19 |
"num_attention_heads": 4,
|
| 20 |
+
"num_hidden_layers": 18,
|
| 21 |
"num_key_value_heads": 1,
|
| 22 |
"pad_token_id": 0,
|
| 23 |
"query_pre_attn_scalar": 256,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b9a4f54c9e2aa3abf1ccc7c1475dde3d7d67688cb01f11c3e3083f927574dd6
|
| 3 |
+
size 1570325296
|