hanzla commited on
Commit
26c7f96
1 Parent(s): cabd6ef

Trained with Unsloth

Browse files
README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - unsloth
9
  - gemma
10
  - trl
 
11
  base_model: google/gemma-2b
12
  ---
13
 
 
8
  - unsloth
9
  - gemma
10
  - trl
11
+ - sft
12
  base_model: google/gemma-2b
13
  ---
14
 
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-2b",
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_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 18,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.38.2",
26
+ "unsloth_version": "2024.3",
27
+ "use_cache": true,
28
+ "vocab_size": 256000
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe080a7b86c5076f0b166f33766c0bfe6258539351e87a70486627e81db68b49
3
+ size 4945280766
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d65bdf60d654f624c077d1884b328fcd798aed517c1fc4620390836c1870f9c
3
+ size 67123512
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
171
+ }
172
+ }