Hugging Face's logo

tomg-group-umd
/
Gemstone-3072x12_cooldown

Text Generation
Transformers
Safetensors
English
gemma
causal-lm
text-generation-inference
Inference Endpoints
Model card Files Community
smcleish commited on
Commit
394e77d
·
verified ·
1 Parent(s): 87f77a4

Upload GemmaForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +32 -0
  2. generation_config.json +7 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +118 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GemmaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": null,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "final_logit_softcapping": null,
11
+ "head_dim": 128,
12
+ "hidden_act": "gelu",
13
+ "hidden_activation": null,
14
+ "hidden_size": 3072,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 12288,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gemma",
19
+ "num_attention_heads": 24,
20
+ "num_hidden_layers": 12,
21
+ "num_key_value_heads": 12,
22
+ "pad_token_id": 0,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.48.2",
30
+ "use_cache": true,
31
+ "vocab_size": 50304
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64ff489b8ddb0446e33ca7c32f14b95591c5526fdf6cd4a4c12772a0e599da7
3
+ size 4997169008
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d870d729a1a4dd15ffd409b284b33bdbb18a8ce3ca715946d2abc2da2f0b4e
3
+ size 3034194528
model.safetensors.index.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8031350784
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.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
44
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.norm.weight": "model-00002-of-00002.safetensors"
117
+ }
118
+ }