k-l-lambda
commited on
Commit
·
c96568f
1
Parent(s):
ec2e07c
updated super parameters.
Browse files- config.json +4 -4
- model.safetensors +2 -2
config.json
CHANGED
@@ -10,17 +10,17 @@
|
|
10 |
128008,
|
11 |
128009
|
12 |
],
|
13 |
-
"head_dim":
|
14 |
"hidden_act": "silu",
|
15 |
-
"hidden_size":
|
16 |
"initializer_range": 0.02,
|
17 |
-
"intermediate_size":
|
18 |
"max_position_embeddings": 131072,
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 4,
|
23 |
-
"num_key_value_heads":
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
"rope_scaling": {
|
|
|
10 |
128008,
|
11 |
128009
|
12 |
],
|
13 |
+
"head_dim": 64,
|
14 |
"hidden_act": "silu",
|
15 |
+
"hidden_size": 512,
|
16 |
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 2048,
|
18 |
"max_position_embeddings": 131072,
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
"num_attention_heads": 32,
|
22 |
"num_hidden_layers": 4,
|
23 |
+
"num_key_value_heads": 2,
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
"rope_scaling": {
|
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 sha256:4ec3fccbc7faf852bdaa09fd4531fbb316f1ab86065d109589109ebb6476c8a7
|
3 |
+
size 174339240
|