Training in progress, epoch 1
Browse files- config.json +4 -4
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -6,14 +6,14 @@
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
-
"hidden_size":
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 256,
|
12 |
"max_position_embeddings": 2048,
|
13 |
"model_type": "llama",
|
14 |
-
"num_attention_heads":
|
15 |
-
"num_hidden_layers":
|
16 |
-
"num_key_value_heads":
|
17 |
"pad_token_id": 2,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
+
"hidden_size": 128,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 256,
|
12 |
"max_position_embeddings": 2048,
|
13 |
"model_type": "llama",
|
14 |
+
"num_attention_heads": 8,
|
15 |
+
"num_hidden_layers": 3,
|
16 |
+
"num_key_value_heads": 8,
|
17 |
"pad_token_id": 2,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
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:b496f88943e84c035c10a32e57a6e60844895677e6449d0545646e87e37855a6
|
3 |
+
size 7092848
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280890a7f5bb8b444428bbcbf9b37681807e561673129c0d859f8582f9bc219b
|
3 |
size 4600
|