Upload 3 files
Browse files- config.json +26 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MOASpecModel"
|
4 |
+
],
|
5 |
+
"head_dim": 128,
|
6 |
+
"hidden_act": "silu",
|
7 |
+
"hidden_size": 4096,
|
8 |
+
"max_position_embeddings": 8192,
|
9 |
+
"mlp_bias": false,
|
10 |
+
"model_type": "moa_spec",
|
11 |
+
"num_attention_heads": 32,
|
12 |
+
"rms_norm_eps": 1e-05,
|
13 |
+
"rope_scaling": null,
|
14 |
+
"rope_theta": 500000.0,
|
15 |
+
"torch_dtype": "bfloat16",
|
16 |
+
"transformers_version": "4.45.2",
|
17 |
+
"vocab_size": 128256,
|
18 |
+
"self_attention_num_key_value_heads": 4,
|
19 |
+
"self_attention_intermediate_size": 6144,
|
20 |
+
"cross_attention_num_key_value_heads": 4,
|
21 |
+
"cross_attention_intermediate_size": 6144,
|
22 |
+
"disable_LSA": false,
|
23 |
+
"kv_hidden_size": 2048,
|
24 |
+
"layer_self_attention_num_key_value_heads": 8,
|
25 |
+
"layer_self_attention_intermediate_size": 3072
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"eos_token_id": [
|
5 |
+
128001,
|
6 |
+
128009
|
7 |
+
],
|
8 |
+
"transformers_version": "4.45.2"
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ba49846f9d9f1e6c3f8070b71d9e37647502be95e01fad6001e9afcc63161ae
|
3 |
+
size 1057066168
|