Upload 6 files
Browse files- .gitattributes +1 -0
- config.json +115 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- processor_config.json +75 -0
- tokenizer.json +3 -0
- tokenizer_config.json +54 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": null,
|
| 6 |
+
"audio_token_id": 258881,
|
| 7 |
+
"boa_token_id": 256000,
|
| 8 |
+
"boi_token_id": 255999,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eoa_token_id": 258883,
|
| 11 |
+
"eoa_token_index": 258883,
|
| 12 |
+
"eoi_token_id": 258882,
|
| 13 |
+
"image_token_id": 258880,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"model_type": "gemma4",
|
| 16 |
+
"text_config": {
|
| 17 |
+
"attention_bias": false,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"attention_k_eq_v": true,
|
| 20 |
+
"bos_token_id": 2,
|
| 21 |
+
"dtype": "float32",
|
| 22 |
+
"enable_moe_block": false,
|
| 23 |
+
"eos_token_id": 1,
|
| 24 |
+
"expert_intermediate_size": null,
|
| 25 |
+
"final_logit_softcapping": 30.0,
|
| 26 |
+
"global_head_dim": 4,
|
| 27 |
+
"head_dim": 4,
|
| 28 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 29 |
+
"hidden_size": 32,
|
| 30 |
+
"hidden_size_per_layer_input": 0,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 64,
|
| 33 |
+
"layer_types": [
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention"
|
| 36 |
+
],
|
| 37 |
+
"max_position_embeddings": 262144,
|
| 38 |
+
"model_type": "gemma4_text",
|
| 39 |
+
"moe_intermediate_size": null,
|
| 40 |
+
"num_attention_heads": 32,
|
| 41 |
+
"num_experts": null,
|
| 42 |
+
"num_global_key_value_heads": 4,
|
| 43 |
+
"num_hidden_layers": 2,
|
| 44 |
+
"num_key_value_heads": 16,
|
| 45 |
+
"num_kv_shared_layers": 0,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"rms_norm_eps": 1e-06,
|
| 48 |
+
"rope_parameters": {
|
| 49 |
+
"full_attention": {
|
| 50 |
+
"partial_rotary_factor": 0.25,
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
+
"rope_type": "proportional"
|
| 53 |
+
},
|
| 54 |
+
"sliding_attention": {
|
| 55 |
+
"rope_theta": 10000.0,
|
| 56 |
+
"rope_type": "default"
|
| 57 |
+
}
|
| 58 |
+
},
|
| 59 |
+
"sliding_window": 1024,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"top_k_experts": null,
|
| 62 |
+
"use_bidirectional_attention": "vision",
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_double_wide_mlp": false,
|
| 65 |
+
"vocab_size": 262144,
|
| 66 |
+
"vocab_size_per_layer_input": 262144
|
| 67 |
+
},
|
| 68 |
+
"tie_word_embeddings": true,
|
| 69 |
+
"transformers_version": "5.5.0",
|
| 70 |
+
"video_token_id": 258884,
|
| 71 |
+
"vision_config": {
|
| 72 |
+
"_name_or_path": "",
|
| 73 |
+
"architectures": null,
|
| 74 |
+
"attention_bias": false,
|
| 75 |
+
"attention_dropout": 0.0,
|
| 76 |
+
"chunk_size_feed_forward": 0,
|
| 77 |
+
"default_output_length": 280,
|
| 78 |
+
"dtype": "bfloat16",
|
| 79 |
+
"global_head_dim": 72,
|
| 80 |
+
"head_dim": 4,
|
| 81 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 82 |
+
"hidden_size": 8,
|
| 83 |
+
"id2label": {
|
| 84 |
+
"0": "LABEL_0",
|
| 85 |
+
"1": "LABEL_1"
|
| 86 |
+
},
|
| 87 |
+
"initializer_range": 0.02,
|
| 88 |
+
"intermediate_size": 32,
|
| 89 |
+
"is_encoder_decoder": false,
|
| 90 |
+
"label2id": {
|
| 91 |
+
"LABEL_0": 0,
|
| 92 |
+
"LABEL_1": 1
|
| 93 |
+
},
|
| 94 |
+
"max_position_embeddings": 131072,
|
| 95 |
+
"model_type": "gemma4_vision",
|
| 96 |
+
"num_attention_heads": 16,
|
| 97 |
+
"num_hidden_layers": 1,
|
| 98 |
+
"num_key_value_heads": 2,
|
| 99 |
+
"output_attentions": false,
|
| 100 |
+
"output_hidden_states": false,
|
| 101 |
+
"patch_size": 16,
|
| 102 |
+
"pooling_kernel_size": 3,
|
| 103 |
+
"position_embedding_size": 10240,
|
| 104 |
+
"problem_type": null,
|
| 105 |
+
"return_dict": true,
|
| 106 |
+
"rms_norm_eps": 1e-06,
|
| 107 |
+
"rope_parameters": {
|
| 108 |
+
"rope_theta": 100.0,
|
| 109 |
+
"rope_type": "default"
|
| 110 |
+
},
|
| 111 |
+
"standardize": true,
|
| 112 |
+
"use_clipped_linears": false
|
| 113 |
+
},
|
| 114 |
+
"vision_soft_tokens_per_image": 280
|
| 115 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "5.5.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1ac51cd571407ff11392a2a8d977ddf1d1eb9fc82b0471bf0c826f3f255619a
|
| 3 |
+
size 34039528
|
processor_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 7 |
+
"feature_size": 128,
|
| 8 |
+
"fft_length": 512,
|
| 9 |
+
"fft_overdrive": false,
|
| 10 |
+
"frame_length": 320,
|
| 11 |
+
"hop_length": 160,
|
| 12 |
+
"input_scale_factor": 1.0,
|
| 13 |
+
"max_frequency": 8000.0,
|
| 14 |
+
"mel_floor": 0.001,
|
| 15 |
+
"min_frequency": 0.0,
|
| 16 |
+
"padding_side": "right",
|
| 17 |
+
"padding_value": 0.0,
|
| 18 |
+
"per_bin_mean": null,
|
| 19 |
+
"per_bin_stddev": null,
|
| 20 |
+
"preemphasis": 0.0,
|
| 21 |
+
"preemphasis_htk_flavor": true,
|
| 22 |
+
"return_attention_mask": true,
|
| 23 |
+
"sampling_rate": 16000
|
| 24 |
+
},
|
| 25 |
+
"image_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": false,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"do_resize": true,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0
|
| 34 |
+
],
|
| 35 |
+
"image_processor_type": "Gemma4ImageProcessor",
|
| 36 |
+
"image_seq_length": 280,
|
| 37 |
+
"image_std": [
|
| 38 |
+
1.0,
|
| 39 |
+
1.0,
|
| 40 |
+
1.0
|
| 41 |
+
],
|
| 42 |
+
"max_soft_tokens": 280,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pooling_kernel_size": 3,
|
| 45 |
+
"resample": 3,
|
| 46 |
+
"rescale_factor": 0.00392156862745098
|
| 47 |
+
},
|
| 48 |
+
"image_seq_length": 280,
|
| 49 |
+
"processor_class": "Gemma4Processor",
|
| 50 |
+
"video_processor": {
|
| 51 |
+
"do_convert_rgb": true,
|
| 52 |
+
"do_normalize": true,
|
| 53 |
+
"do_rescale": true,
|
| 54 |
+
"do_resize": true,
|
| 55 |
+
"do_sample_frames": true,
|
| 56 |
+
"image_mean": [
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0
|
| 60 |
+
],
|
| 61 |
+
"image_std": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"max_soft_tokens": 70,
|
| 67 |
+
"num_frames": 32,
|
| 68 |
+
"patch_size": 16,
|
| 69 |
+
"pooling_kernel_size": 3,
|
| 70 |
+
"resample": 3,
|
| 71 |
+
"rescale_factor": 0.00392156862745098,
|
| 72 |
+
"return_metadata": false,
|
| 73 |
+
"video_processor_type": "Gemma4VideoProcessor"
|
| 74 |
+
}
|
| 75 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
|
| 3 |
+
size 32170070
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": false,
|
| 21 |
+
"mask_token": "<mask>",
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"model_specific_special_tokens": {
|
| 24 |
+
"audio_token": "<|audio|>",
|
| 25 |
+
"boa_token": "<|audio>",
|
| 26 |
+
"boi_token": "<|image>",
|
| 27 |
+
"eoa_token": "<audio|>",
|
| 28 |
+
"eoc_token": "<channel|>",
|
| 29 |
+
"eoi_token": "<image|>",
|
| 30 |
+
"eot_token": "<turn|>",
|
| 31 |
+
"escape_token": "<|\"|>",
|
| 32 |
+
"etc_token": "<tool_call|>",
|
| 33 |
+
"etd_token": "<tool|>",
|
| 34 |
+
"etr_token": "<tool_response|>",
|
| 35 |
+
"image_token": "<|image|>",
|
| 36 |
+
"soc_token": "<|channel>",
|
| 37 |
+
"sot_token": "<|turn>",
|
| 38 |
+
"stc_token": "<|tool_call>",
|
| 39 |
+
"std_token": "<|tool>",
|
| 40 |
+
"str_token": "<|tool_response>",
|
| 41 |
+
"think_token": "<|think|>"
|
| 42 |
+
},
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"padding_side": "left",
|
| 45 |
+
"processor_class": "Gemma4Processor",
|
| 46 |
+
"soc_token": "<|channel>",
|
| 47 |
+
"sot_token": "<|turn>",
|
| 48 |
+
"stc_token": "<|tool_call>",
|
| 49 |
+
"std_token": "<|tool>",
|
| 50 |
+
"str_token": "<|tool_response>",
|
| 51 |
+
"think_token": "<|think|>",
|
| 52 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 53 |
+
"unk_token": "<unk>"
|
| 54 |
+
}
|