Upload folder using huggingface_hub
Browse files- config.json +21 -9
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +16 -32
- tokenizer.json +0 -0
config.json
CHANGED
@@ -2,17 +2,29 @@
|
|
2 |
"architectures": [
|
3 |
"Gemma2Model"
|
4 |
],
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
"model_type": "gemma2",
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
|
|
|
|
|
|
15 |
"torch_dtype": "float32",
|
16 |
"transformers_version": "4.42.3",
|
|
|
17 |
"vocab_size": 50257
|
18 |
}
|
|
|
2 |
"architectures": [
|
3 |
"Gemma2Model"
|
4 |
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"attn_logit_softcapping": 50.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"final_logit_softcapping": 30.0,
|
11 |
+
"head_dim": 256,
|
12 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
13 |
+
"hidden_size": 3072,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 24576,
|
16 |
+
"max_position_embeddings": 8192,
|
17 |
"model_type": "gemma2",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 28,
|
20 |
+
"num_key_value_heads": 16,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"query_pre_attn_scalar": 224,
|
23 |
+
"rms_norm_eps": 1e-06,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"sliding_window": 4096,
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.42.3",
|
28 |
+
"use_cache": true,
|
29 |
"vocab_size": 50257
|
30 |
}
|
model-00001-of-00002.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:a77ca0e8ea5b3455808c2042946fdbbe9338a267a3c0fc6b74df10e569eb6623
|
3 |
+
size 4946115520
|
model-00002-of-00002.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:e804047dad69e495540b3cb78a86936d5ca3323b212ae5d5c85db4480447bdac
|
3 |
+
size 617558144
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embeddings.weight": "model-00001-of-00002.safetensors",
|
@@ -73,41 +73,25 @@
|
|
73 |
"layers.23.wq.weight": "model-00001-of-00002.safetensors",
|
74 |
"layers.23.wv.weight": "model-00001-of-00002.safetensors",
|
75 |
"layers.24.wk.weight": "model-00001-of-00002.safetensors",
|
76 |
-
"layers.24.wo.weight": "model-
|
77 |
"layers.24.wq.weight": "model-00001-of-00002.safetensors",
|
78 |
"layers.24.wv.weight": "model-00001-of-00002.safetensors",
|
79 |
-
"layers.25.wk.weight": "model-
|
80 |
-
"layers.25.wo.weight": "model-
|
81 |
-
"layers.25.wq.weight": "model-
|
82 |
-
"layers.25.wv.weight": "model-
|
83 |
-
"layers.26.wk.weight": "model-
|
84 |
-
"layers.26.wo.weight": "model-
|
85 |
-
"layers.26.wq.weight": "model-
|
86 |
-
"layers.26.wv.weight": "model-
|
87 |
-
"layers.27.wk.weight": "model-
|
88 |
-
"layers.27.wo.weight": "model-
|
89 |
-
"layers.27.wq.weight": "model-
|
90 |
-
"layers.27.wv.weight": "model-
|
91 |
-
"layers.28.wk.weight": "model-00002-of-00002.safetensors",
|
92 |
-
"layers.28.wo.weight": "model-00002-of-00002.safetensors",
|
93 |
-
"layers.28.wq.weight": "model-00002-of-00002.safetensors",
|
94 |
-
"layers.28.wv.weight": "model-00002-of-00002.safetensors",
|
95 |
-
"layers.29.wk.weight": "model-00002-of-00002.safetensors",
|
96 |
-
"layers.29.wo.weight": "model-00002-of-00002.safetensors",
|
97 |
-
"layers.29.wq.weight": "model-00002-of-00002.safetensors",
|
98 |
-
"layers.29.wv.weight": "model-00002-of-00002.safetensors",
|
99 |
"layers.3.wk.weight": "model-00001-of-00002.safetensors",
|
100 |
"layers.3.wo.weight": "model-00001-of-00002.safetensors",
|
101 |
"layers.3.wq.weight": "model-00001-of-00002.safetensors",
|
102 |
"layers.3.wv.weight": "model-00001-of-00002.safetensors",
|
103 |
-
"layers.30.wk.weight": "model-00002-of-00002.safetensors",
|
104 |
-
"layers.30.wo.weight": "model-00002-of-00002.safetensors",
|
105 |
-
"layers.30.wq.weight": "model-00002-of-00002.safetensors",
|
106 |
-
"layers.30.wv.weight": "model-00002-of-00002.safetensors",
|
107 |
-
"layers.31.wk.weight": "model-00002-of-00002.safetensors",
|
108 |
-
"layers.31.wo.weight": "model-00002-of-00002.safetensors",
|
109 |
-
"layers.31.wq.weight": "model-00002-of-00002.safetensors",
|
110 |
-
"layers.31.wv.weight": "model-00002-of-00002.safetensors",
|
111 |
"layers.4.wk.weight": "model-00001-of-00002.safetensors",
|
112 |
"layers.4.wo.weight": "model-00001-of-00002.safetensors",
|
113 |
"layers.4.wq.weight": "model-00001-of-00002.safetensors",
|
@@ -133,8 +117,8 @@
|
|
133 |
"layers.9.wq.weight": "model-00001-of-00002.safetensors",
|
134 |
"layers.9.wv.weight": "model-00001-of-00002.safetensors",
|
135 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
136 |
-
"ln_f.bias": "model-
|
137 |
-
"ln_f.weight": "model-
|
138 |
"pos_embeddings.weight": "model-00001-of-00002.safetensors"
|
139 |
}
|
140 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 5563662336
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"embeddings.weight": "model-00001-of-00002.safetensors",
|
|
|
73 |
"layers.23.wq.weight": "model-00001-of-00002.safetensors",
|
74 |
"layers.23.wv.weight": "model-00001-of-00002.safetensors",
|
75 |
"layers.24.wk.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"layers.24.wo.weight": "model-00001-of-00002.safetensors",
|
77 |
"layers.24.wq.weight": "model-00001-of-00002.safetensors",
|
78 |
"layers.24.wv.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"layers.25.wk.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"layers.25.wo.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"layers.25.wq.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"layers.25.wv.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"layers.26.wk.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"layers.26.wo.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"layers.26.wq.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"layers.26.wv.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"layers.27.wk.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"layers.27.wo.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"layers.27.wq.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"layers.27.wv.weight": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
"layers.3.wk.weight": "model-00001-of-00002.safetensors",
|
92 |
"layers.3.wo.weight": "model-00001-of-00002.safetensors",
|
93 |
"layers.3.wq.weight": "model-00001-of-00002.safetensors",
|
94 |
"layers.3.wv.weight": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
95 |
"layers.4.wk.weight": "model-00001-of-00002.safetensors",
|
96 |
"layers.4.wo.weight": "model-00001-of-00002.safetensors",
|
97 |
"layers.4.wq.weight": "model-00001-of-00002.safetensors",
|
|
|
117 |
"layers.9.wq.weight": "model-00001-of-00002.safetensors",
|
118 |
"layers.9.wv.weight": "model-00001-of-00002.safetensors",
|
119 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
120 |
+
"ln_f.bias": "model-00001-of-00002.safetensors",
|
121 |
+
"ln_f.weight": "model-00001-of-00002.safetensors",
|
122 |
"pos_embeddings.weight": "model-00001-of-00002.safetensors"
|
123 |
}
|
124 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|