Upload GemmaForCausalLM
Browse files- config.json +18 -129
- generation_config.json +3 -7
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +94 -125
config.json
CHANGED
@@ -1,140 +1,29 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "./checkpoints-functions-full",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
-
"
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
"bos_token_id": 1,
|
15 |
-
"embd_pdrop": 0.0,
|
16 |
-
"eos_token_id": 32000,
|
17 |
-
"hidden_act": "silu",
|
18 |
-
"hidden_size": 3072,
|
19 |
"initializer_range": 0.02,
|
20 |
-
"intermediate_size":
|
21 |
-
"max_position_embeddings":
|
22 |
-
"model_type": "
|
23 |
-
"num_attention_heads":
|
24 |
-
"num_hidden_layers":
|
25 |
-
"num_key_value_heads":
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"rms_norm_eps": 1e-05,
|
30 |
-
"rope_scaling": {
|
31 |
-
"long_factor": [
|
32 |
-
1.0299999713897705,
|
33 |
-
1.0499999523162842,
|
34 |
-
1.0499999523162842,
|
35 |
-
1.0799999237060547,
|
36 |
-
1.2299998998641968,
|
37 |
-
1.2299998998641968,
|
38 |
-
1.2999999523162842,
|
39 |
-
1.4499999284744263,
|
40 |
-
1.5999999046325684,
|
41 |
-
1.6499998569488525,
|
42 |
-
1.8999998569488525,
|
43 |
-
2.859999895095825,
|
44 |
-
3.68999981880188,
|
45 |
-
5.419999599456787,
|
46 |
-
5.489999771118164,
|
47 |
-
5.489999771118164,
|
48 |
-
9.09000015258789,
|
49 |
-
11.579999923706055,
|
50 |
-
15.65999984741211,
|
51 |
-
15.769999504089355,
|
52 |
-
15.789999961853027,
|
53 |
-
18.360000610351562,
|
54 |
-
21.989999771118164,
|
55 |
-
23.079999923706055,
|
56 |
-
30.009998321533203,
|
57 |
-
32.35000228881836,
|
58 |
-
32.590003967285156,
|
59 |
-
35.56000518798828,
|
60 |
-
39.95000457763672,
|
61 |
-
53.840003967285156,
|
62 |
-
56.20000457763672,
|
63 |
-
57.95000457763672,
|
64 |
-
59.29000473022461,
|
65 |
-
59.77000427246094,
|
66 |
-
59.920005798339844,
|
67 |
-
61.190006256103516,
|
68 |
-
61.96000671386719,
|
69 |
-
62.50000762939453,
|
70 |
-
63.3700065612793,
|
71 |
-
63.48000717163086,
|
72 |
-
63.48000717163086,
|
73 |
-
63.66000747680664,
|
74 |
-
63.850006103515625,
|
75 |
-
64.08000946044922,
|
76 |
-
64.760009765625,
|
77 |
-
64.80001068115234,
|
78 |
-
64.81001281738281,
|
79 |
-
64.81001281738281
|
80 |
-
],
|
81 |
-
"short_factor": [
|
82 |
-
1.05,
|
83 |
-
1.05,
|
84 |
-
1.05,
|
85 |
-
1.1,
|
86 |
-
1.1,
|
87 |
-
1.1500000000000001,
|
88 |
-
1.2000000000000002,
|
89 |
-
1.2500000000000002,
|
90 |
-
1.3000000000000003,
|
91 |
-
1.3500000000000003,
|
92 |
-
1.5000000000000004,
|
93 |
-
2.000000000000001,
|
94 |
-
2.000000000000001,
|
95 |
-
2.000000000000001,
|
96 |
-
2.000000000000001,
|
97 |
-
2.000000000000001,
|
98 |
-
2.000000000000001,
|
99 |
-
2.000000000000001,
|
100 |
-
2.000000000000001,
|
101 |
-
2.000000000000001,
|
102 |
-
2.000000000000001,
|
103 |
-
2.000000000000001,
|
104 |
-
2.000000000000001,
|
105 |
-
2.000000000000001,
|
106 |
-
2.000000000000001,
|
107 |
-
2.000000000000001,
|
108 |
-
2.000000000000001,
|
109 |
-
2.000000000000001,
|
110 |
-
2.000000000000001,
|
111 |
-
2.000000000000001,
|
112 |
-
2.000000000000001,
|
113 |
-
2.000000000000001,
|
114 |
-
2.0500000000000007,
|
115 |
-
2.0500000000000007,
|
116 |
-
2.0500000000000007,
|
117 |
-
2.1000000000000005,
|
118 |
-
2.1000000000000005,
|
119 |
-
2.1000000000000005,
|
120 |
-
2.1500000000000004,
|
121 |
-
2.1500000000000004,
|
122 |
-
2.3499999999999996,
|
123 |
-
2.549999999999999,
|
124 |
-
2.5999999999999988,
|
125 |
-
2.5999999999999988,
|
126 |
-
2.7499999999999982,
|
127 |
-
2.849999999999998,
|
128 |
-
2.849999999999998,
|
129 |
-
2.9499999999999975
|
130 |
-
],
|
131 |
-
"type": "su"
|
132 |
-
},
|
133 |
"rope_theta": 10000.0,
|
134 |
-
"sliding_window": 262144,
|
135 |
-
"tie_word_embeddings": false,
|
136 |
"torch_dtype": "bfloat16",
|
137 |
"transformers_version": "4.39.3",
|
138 |
"use_cache": false,
|
139 |
-
"vocab_size":
|
140 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./checkpoints-functions-full-v2",
|
3 |
"architectures": [
|
4 |
+
"GemmaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"eos_token_id": 1,
|
10 |
+
"head_dim": 256,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_activation": null,
|
13 |
+
"hidden_size": 2048,
|
|
|
|
|
|
|
|
|
|
|
14 |
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 16384,
|
16 |
+
"max_position_embeddings": 8192,
|
17 |
+
"model_type": "gemma",
|
18 |
+
"num_attention_heads": 8,
|
19 |
+
"num_hidden_layers": 18,
|
20 |
+
"num_key_value_heads": 1,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"rope_theta": 10000.0,
|
|
|
|
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.39.3",
|
27 |
"use_cache": false,
|
28 |
+
"vocab_size": 256000
|
29 |
}
|
generation_config.json
CHANGED
@@ -1,11 +1,7 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
-
|
6 |
-
32001,
|
7 |
-
32007
|
8 |
-
],
|
9 |
-
"pad_token_id": 32000,
|
10 |
"transformers_version": "4.39.3"
|
11 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
6 |
"transformers_version": "4.39.3"
|
7 |
}
|
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:f89e4915a5c613466549f65b6da08cbeb5c68f302fb24a18b76d4921610f19d7
|
3 |
+
size 4945242264
|
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 sha256:762ac6c40670c04c6c1fcdb7902df808a8b765cc3383663412664059246ddb68
|
3 |
+
size 67121608
|
model.safetensors.index.json
CHANGED
@@ -1,202 +1,171 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
-
"lm_head.weight": "model-00002-of-00002.safetensors",
|
7 |
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
8 |
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
9 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
-
"model.layers.0.mlp.
|
|
|
11 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
12 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
-
"model.layers.0.self_attn.
|
|
|
14 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
15 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
-
"model.layers.1.mlp.
|
|
|
17 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
18 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
-
"model.layers.1.self_attn.
|
|
|
20 |
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
21 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
-
"model.layers.10.mlp.
|
|
|
23 |
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
24 |
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
-
"model.layers.10.self_attn.
|
|
|
26 |
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
27 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
-
"model.layers.11.mlp.
|
|
|
29 |
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
30 |
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
-
"model.layers.11.self_attn.
|
|
|
32 |
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
33 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
-
"model.layers.12.mlp.
|
|
|
35 |
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
36 |
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
-
"model.layers.12.self_attn.
|
|
|
38 |
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
39 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
-
"model.layers.13.mlp.
|
|
|
41 |
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
42 |
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
-
"model.layers.13.self_attn.
|
|
|
44 |
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
45 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
-
"model.layers.14.mlp.
|
|
|
47 |
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
48 |
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
-
"model.layers.14.self_attn.
|
|
|
50 |
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
51 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
-
"model.layers.15.mlp.
|
|
|
53 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
54 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
-
"model.layers.15.self_attn.
|
|
|
56 |
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
58 |
-
"model.layers.16.mlp.
|
|
|
59 |
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
60 |
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
-
"model.layers.16.self_attn.
|
62 |
-
"model.layers.
|
63 |
-
"model.layers.17.
|
64 |
-
"model.layers.17.mlp.
|
65 |
-
"model.layers.17.
|
|
|
|
|
|
|
66 |
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
-
"model.layers.17.self_attn.
|
68 |
-
"model.layers.
|
69 |
-
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
-
"model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
71 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
72 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
-
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
-
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
75 |
-
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
76 |
-
"model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
78 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
-
"model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
81 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
-
"model.layers.2.mlp.
|
|
|
83 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
84 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
85 |
-
"model.layers.2.self_attn.
|
86 |
-
"model.layers.
|
87 |
-
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
-
"model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
90 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
-
"model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
-
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
93 |
-
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
94 |
-
"model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
95 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
96 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
-
"model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
98 |
-
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
99 |
-
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
100 |
-
"model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
101 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
102 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
103 |
-
"model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
104 |
-
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
105 |
-
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
106 |
-
"model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
107 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
108 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
109 |
-
"model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
110 |
-
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
111 |
-
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
112 |
-
"model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
113 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
114 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
115 |
-
"model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
116 |
-
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
117 |
-
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
118 |
-
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
119 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
120 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
121 |
-
"model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
122 |
-
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
123 |
-
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
124 |
-
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
125 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
126 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
127 |
-
"model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
128 |
-
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
129 |
-
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
130 |
-
"model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
131 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
132 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
133 |
-
"model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
134 |
-
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
135 |
-
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
136 |
-
"model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
138 |
-
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
139 |
-
"model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
140 |
-
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
141 |
-
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
142 |
-
"model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
-
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
144 |
-
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
145 |
-
"model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
146 |
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
147 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
148 |
-
"model.layers.3.mlp.
|
|
|
149 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
150 |
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
-
"model.layers.3.self_attn.
|
152 |
-
"model.layers.
|
153 |
-
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
154 |
-
"model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
155 |
-
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
156 |
-
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
157 |
-
"model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
158 |
-
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
159 |
-
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
160 |
-
"model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
161 |
-
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
162 |
-
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
163 |
-
"model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
164 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
165 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
-
"model.layers.4.mlp.
|
|
|
167 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
168 |
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
-
"model.layers.4.self_attn.
|
|
|
170 |
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
171 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
-
"model.layers.5.mlp.
|
|
|
173 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
174 |
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
-
"model.layers.5.self_attn.
|
|
|
176 |
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
177 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
-
"model.layers.6.mlp.
|
|
|
179 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
180 |
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
-
"model.layers.6.self_attn.
|
|
|
182 |
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
183 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
184 |
-
"model.layers.7.mlp.
|
|
|
185 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
186 |
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
-
"model.layers.7.self_attn.
|
|
|
188 |
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
189 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
-
"model.layers.8.mlp.
|
|
|
191 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
192 |
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
-
"model.layers.8.self_attn.
|
|
|
194 |
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
195 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
-
"model.layers.9.mlp.
|
|
|
197 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
|
|
198 |
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
-
"model.layers.9.self_attn.
|
|
|
200 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
201 |
}
|
202 |
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 5012344832
|
4 |
},
|
5 |
"weight_map": {
|
|
|
6 |
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
7 |
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
8 |
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
17 |
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
26 |
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
35 |
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
44 |
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
53 |
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
58 |
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
62 |
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
71 |
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
76 |
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
80 |
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
85 |
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
94 |
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
98 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
101 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
103 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
107 |
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
110 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
112 |
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
116 |
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
117 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
119 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
121 |
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
122 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
125 |
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
128 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
130 |
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
133 |
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
134 |
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
135 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
136 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
138 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
139 |
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
140 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
143 |
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
144 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
146 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
148 |
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
152 |
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
154 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
155 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
156 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
157 |
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
160 |
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
161 |
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
162 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
164 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
"model.norm.weight": "model-00002-of-00002.safetensors"
|
170 |
}
|
171 |
}
|