Hugging Face's logo

Aravindan
/
gemma-2b-instruct-fiqa

Text Generation
Transformers
Safetensors
gemma
text-generation-inference
Model card Files
xet
 Community
Aravindan commited on
Commit
7b99ce8
·
verified ·
1 Parent(s): 2b62677

Upload GemmaForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +2 -2
  2. generation_config.json +1 -1
  3. model-00001-of-00002.safetensors +2 -2
  4. model-00002-of-00002.safetensors +2 -2
  5. model.safetensors.index.json +82 -82
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "rope_scaling": null,
24
  "rope_theta": 10000.0,
25
  "torch_dtype": "float16",
26
- "transformers_version": "4.42.0.dev0",
27
  "use_cache": true,
28
- "vocab_size": 256008
29
  }
 
23
  "rope_scaling": null,
24
  "rope_theta": 10000.0,
25
  "torch_dtype": "float16",
26
+ "transformers_version": "4.41.2",
27
  "use_cache": true,
28
+ "vocab_size": 256000
29
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 2,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.42.0.dev0"
7
  }
 
3
  "bos_token_id": 2,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.41.2"
7
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97d0f4ff13aefd2b9e1eac807f314c9284ef6fdd30cf6d99cc6f31bb2664e730
3
- size 4878082904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf33fc0660c15c8705bd12210856653a00f1c1303690aa24af7dd61ed4b4c5c6
3
+ size 4945242104
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cd9ad48bdc49d17d3a613b0e0f5f21a24e285863f60aff1bd584e8832db3375
3
- size 4097930816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5878fcd2e7e609e0d5d5bf539fb5f02f24b0c5a7014b1efde2f2fd766abade1
3
+ size 67121600
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 8975994880
4
  },
5
  "weight_map": {
6
  "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -22,78 +22,78 @@
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-00002-of-00002.safetensors",
26
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
27
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
28
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
29
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
30
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
31
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
32
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
33
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
34
- "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
35
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
36
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
37
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
38
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
39
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
40
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
41
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
42
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
43
- "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
44
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
45
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
46
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
47
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
48
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
49
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
50
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
51
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
52
- "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
53
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
54
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
55
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
56
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
57
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
58
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
59
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
60
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
61
- "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
62
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
63
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
64
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
65
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
66
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
67
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
68
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
69
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
70
- "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
71
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
72
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
73
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
74
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
75
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
76
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
77
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
78
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
79
- "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
80
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
81
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
82
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
83
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
84
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
85
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
86
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
87
- "model.layers.16.self_attn.v_proj.weight": "model-00002-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-00002-of-00002.safetensors",
91
- "model.layers.17.mlp.up_proj.weight": "model-00002-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-00002-of-00002.safetensors",
94
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
95
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
96
- "model.layers.17.self_attn.v_proj.weight": "model-00002-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",
@@ -148,24 +148,24 @@
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-00002-of-00002.safetensors",
152
- "model.layers.8.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
161
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
  "model.norm.weight": "model-00002-of-00002.safetensors"
170
  }
171
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 5012344832
4
  },
5
  "weight_map": {
6
  "model.embed_tokens.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",
 
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
  }