Hugging Face's logo

bjivanovich
/
Gemma4-E2B-Vision-LoRA

Image-Text-to-Text
Transformers
Safetensors
English
gemma4
text-generation-inference
unsloth
trl
sft
conversational
Model card Files
xet
 Community
bjivanovich commited on
Commit
15f04f8
·
verified ·
1 Parent(s): 070a83f

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +194 -0
  3. generation_config.json +14 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - gemma4
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - gemma4
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "_name_or_path": "",
7
+ "architectures": null,
8
+ "attention_chunk_size": 12,
9
+ "attention_context_left": 13,
10
+ "attention_context_right": 0,
11
+ "attention_invalid_logits_value": -1000000000.0,
12
+ "attention_logit_cap": 50.0,
13
+ "chunk_size_feed_forward": 0,
14
+ "conv_kernel_size": 5,
15
+ "dtype": "bfloat16",
16
+ "gradient_clipping": 10000000000.0,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "is_encoder_decoder": false,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1
28
+ },
29
+ "model_type": "gemma4_audio",
30
+ "num_attention_heads": 8,
31
+ "num_hidden_layers": 12,
32
+ "output_attentions": false,
33
+ "output_hidden_states": false,
34
+ "output_proj_dims": 1536,
35
+ "problem_type": null,
36
+ "residual_weight": 0.5,
37
+ "return_dict": true,
38
+ "rms_norm_eps": 1e-06,
39
+ "subsampling_conv_channels": [
40
+ 128,
41
+ 32
42
+ ],
43
+ "use_clipped_linears": true
44
+ },
45
+ "audio_token_id": 258881,
46
+ "boa_token_id": 256000,
47
+ "boi_token_id": 255999,
48
+ "bos_token_id": 2,
49
+ "dtype": "bfloat16",
50
+ "eoa_token_id": 258883,
51
+ "eoa_token_index": 258883,
52
+ "eoi_token_id": 258882,
53
+ "eos_token_id": 106,
54
+ "image_token_id": 258880,
55
+ "initializer_range": 0.02,
56
+ "model_name": "unsloth/gemma-4-E2B-it",
57
+ "model_type": "gemma4",
58
+ "pad_token_id": 0,
59
+ "text_config": {
60
+ "attention_bias": false,
61
+ "attention_dropout": 0.0,
62
+ "attention_k_eq_v": false,
63
+ "bos_token_id": 2,
64
+ "dtype": "bfloat16",
65
+ "enable_moe_block": false,
66
+ "eos_token_id": 1,
67
+ "expert_intermediate_size": null,
68
+ "final_logit_softcapping": 30.0,
69
+ "global_head_dim": 512,
70
+ "head_dim": 256,
71
+ "hidden_activation": "gelu_pytorch_tanh",
72
+ "hidden_size": 1536,
73
+ "hidden_size_per_layer_input": 256,
74
+ "initializer_range": 0.02,
75
+ "intermediate_size": 6144,
76
+ "layer_types": [
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "full_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "full_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "full_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "full_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "full_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "full_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "full_attention"
112
+ ],
113
+ "max_position_embeddings": 131072,
114
+ "model_type": "gemma4_text",
115
+ "moe_intermediate_size": null,
116
+ "num_attention_heads": 8,
117
+ "num_experts": null,
118
+ "num_global_key_value_heads": null,
119
+ "num_hidden_layers": 35,
120
+ "num_key_value_heads": 1,
121
+ "num_kv_shared_layers": 20,
122
+ "pad_token_id": 0,
123
+ "rms_norm_eps": 1e-06,
124
+ "rope_parameters": {
125
+ "full_attention": {
126
+ "partial_rotary_factor": 0.25,
127
+ "rope_theta": 1000000.0,
128
+ "rope_type": "proportional"
129
+ },
130
+ "sliding_attention": {
131
+ "rope_theta": 10000.0,
132
+ "rope_type": "default"
133
+ }
134
+ },
135
+ "sliding_window": 512,
136
+ "tie_word_embeddings": true,
137
+ "top_k_experts": null,
138
+ "use_bidirectional_attention": null,
139
+ "use_cache": true,
140
+ "use_double_wide_mlp": true,
141
+ "vocab_size": 262144,
142
+ "vocab_size_per_layer_input": 262144
143
+ },
144
+ "tie_word_embeddings": true,
145
+ "transformers_version": "5.5.0",
146
+ "unsloth_fixed": true,
147
+ "unsloth_version": "2026.4.4",
148
+ "use_cache": false,
149
+ "video_token_id": 258884,
150
+ "vision_config": {
151
+ "_name_or_path": "",
152
+ "architectures": null,
153
+ "attention_bias": false,
154
+ "attention_dropout": 0.0,
155
+ "chunk_size_feed_forward": 0,
156
+ "default_output_length": 280,
157
+ "dtype": "bfloat16",
158
+ "global_head_dim": 64,
159
+ "head_dim": 64,
160
+ "hidden_activation": "gelu_pytorch_tanh",
161
+ "hidden_size": 768,
162
+ "id2label": {
163
+ "0": "LABEL_0",
164
+ "1": "LABEL_1"
165
+ },
166
+ "initializer_range": 0.02,
167
+ "intermediate_size": 3072,
168
+ "is_encoder_decoder": false,
169
+ "label2id": {
170
+ "LABEL_0": 0,
171
+ "LABEL_1": 1
172
+ },
173
+ "max_position_embeddings": 131072,
174
+ "model_type": "gemma4_vision",
175
+ "num_attention_heads": 12,
176
+ "num_hidden_layers": 16,
177
+ "num_key_value_heads": 12,
178
+ "output_attentions": false,
179
+ "output_hidden_states": false,
180
+ "patch_size": 16,
181
+ "pooling_kernel_size": 3,
182
+ "position_embedding_size": 10240,
183
+ "problem_type": null,
184
+ "return_dict": true,
185
+ "rms_norm_eps": 1e-06,
186
+ "rope_parameters": {
187
+ "rope_theta": 100.0,
188
+ "rope_type": "default"
189
+ },
190
+ "standardize": false,
191
+ "use_clipped_linears": true
192
+ },
193
+ "vision_soft_tokens_per_image": 280
194
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106,
7
+ 50
8
+ ],
9
+ "pad_token_id": 0,
10
+ "temperature": 1.0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "5.5.0"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d093ca0499f82236f6efaa0dbeaa27c7809ff759cbe8441c801d02614f670c
3
+ size 10247452942