Add files using upload-large-folder tool
Browse files- config.json +25 -5
- tokenizer_config.json +2 -1
config.json
CHANGED
@@ -3,40 +3,60 @@
|
|
3 |
"Gemma3ForConditionalGeneration"
|
4 |
],
|
5 |
"boi_token_index": 255999,
|
|
|
6 |
"eoi_token_index": 256000,
|
7 |
-
"eos_token_id":
|
8 |
-
1,
|
9 |
-
106
|
10 |
-
],
|
11 |
"image_token_index": 262144,
|
12 |
"initializer_range": 0.02,
|
13 |
"mm_tokens_per_image": 256,
|
14 |
"model_type": "gemma3",
|
|
|
15 |
"text_config": {
|
|
|
|
|
|
|
|
|
|
|
16 |
"head_dim": 128,
|
|
|
17 |
"hidden_size": 5376,
|
|
|
18 |
"intermediate_size": 21504,
|
|
|
19 |
"model_type": "gemma3_text",
|
20 |
"num_attention_heads": 32,
|
21 |
"num_hidden_layers": 62,
|
22 |
"num_key_value_heads": 16,
|
23 |
"query_pre_attn_scalar": 168,
|
|
|
|
|
24 |
"rope_scaling": {
|
25 |
"factor": 8.0,
|
26 |
"rope_type": "linear"
|
27 |
},
|
28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
29 |
},
|
30 |
"torch_dtype": "bfloat16",
|
31 |
"transformers_version": "4.50.0.dev0",
|
|
|
32 |
"vision_config": {
|
|
|
|
|
33 |
"hidden_size": 1152,
|
34 |
"image_size": 896,
|
35 |
"intermediate_size": 4304,
|
|
|
36 |
"model_type": "siglip_vision_model",
|
37 |
"num_attention_heads": 16,
|
|
|
38 |
"num_hidden_layers": 27,
|
39 |
"patch_size": 14,
|
|
|
40 |
"vision_use_head": false
|
41 |
}
|
42 |
}
|
|
|
3 |
"Gemma3ForConditionalGeneration"
|
4 |
],
|
5 |
"boi_token_index": 255999,
|
6 |
+
"bos_token_id": 2,
|
7 |
"eoi_token_index": 256000,
|
8 |
+
"eos_token_id": 1,
|
|
|
|
|
|
|
9 |
"image_token_index": 262144,
|
10 |
"initializer_range": 0.02,
|
11 |
"mm_tokens_per_image": 256,
|
12 |
"model_type": "gemma3",
|
13 |
+
"pad_token_id": 0,
|
14 |
"text_config": {
|
15 |
+
"attention_bias": false,
|
16 |
+
"attention_dropout": 0.0,
|
17 |
+
"attn_logit_softcapping": null,
|
18 |
+
"cache_implementation": "hybrid",
|
19 |
+
"final_logit_softcapping": null,
|
20 |
"head_dim": 128,
|
21 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
22 |
"hidden_size": 5376,
|
23 |
+
"initializer_range": 0.02,
|
24 |
"intermediate_size": 21504,
|
25 |
+
"max_position_embeddings": 131072,
|
26 |
"model_type": "gemma3_text",
|
27 |
"num_attention_heads": 32,
|
28 |
"num_hidden_layers": 62,
|
29 |
"num_key_value_heads": 16,
|
30 |
"query_pre_attn_scalar": 168,
|
31 |
+
"rms_norm_eps": 1e-06,
|
32 |
+
"rope_local_base_freq": 10000.0,
|
33 |
"rope_scaling": {
|
34 |
"factor": 8.0,
|
35 |
"rope_type": "linear"
|
36 |
},
|
37 |
+
"rope_theta": 1000000.0,
|
38 |
+
"sliding_window": 1024,
|
39 |
+
"sliding_window_pattern": 6,
|
40 |
+
"torch_dtype": "bfloat16",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 262208
|
43 |
},
|
44 |
"torch_dtype": "bfloat16",
|
45 |
"transformers_version": "4.50.0.dev0",
|
46 |
+
"unsloth_fixed": true,
|
47 |
"vision_config": {
|
48 |
+
"attention_dropout": 0.0,
|
49 |
+
"hidden_act": "gelu_pytorch_tanh",
|
50 |
"hidden_size": 1152,
|
51 |
"image_size": 896,
|
52 |
"intermediate_size": 4304,
|
53 |
+
"layer_norm_eps": 1e-06,
|
54 |
"model_type": "siglip_vision_model",
|
55 |
"num_attention_heads": 16,
|
56 |
+
"num_channels": 3,
|
57 |
"num_hidden_layers": 27,
|
58 |
"patch_size": 14,
|
59 |
+
"torch_dtype": "bfloat16",
|
60 |
"vision_use_head": false
|
61 |
}
|
62 |
}
|
tokenizer_config.json
CHANGED
@@ -51335,8 +51335,9 @@
|
|
51335 |
"image_token": "<image_soft_token>"
|
51336 |
},
|
51337 |
"image_token": "<image_soft_token>",
|
51338 |
-
"model_max_length":
|
51339 |
"pad_token": "<pad>",
|
|
|
51340 |
"processor_class": "Gemma3Processor",
|
51341 |
"sp_model_kwargs": null,
|
51342 |
"spaces_between_special_tokens": false,
|
|
|
51335 |
"image_token": "<image_soft_token>"
|
51336 |
},
|
51337 |
"image_token": "<image_soft_token>",
|
51338 |
+
"model_max_length": 131072,
|
51339 |
"pad_token": "<pad>",
|
51340 |
+
"padding_side": "left",
|
51341 |
"processor_class": "Gemma3Processor",
|
51342 |
"sp_model_kwargs": null,
|
51343 |
"spaces_between_special_tokens": false,
|