Upload Gemma3ForConditionalGeneration
Browse files- config.json +50 -10
- generation_config.json +4 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -4,6 +4,10 @@
|
|
| 4 |
],
|
| 5 |
"boi_token_index": 255999,
|
| 6 |
"eoi_token_index": 256000,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"image_token_index": 262144,
|
| 8 |
"initializer_range": 0.02,
|
| 9 |
"mm_tokens_per_image": 256,
|
|
@@ -18,24 +22,59 @@
|
|
| 18 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 19 |
"hidden_size": 16,
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
-
"intermediate_size":
|
| 22 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"sliding_attention",
|
| 24 |
"sliding_attention"
|
| 25 |
],
|
| 26 |
"max_position_embeddings": 131072,
|
| 27 |
"model_type": "gemma3_text",
|
| 28 |
-
"num_attention_heads":
|
| 29 |
"num_hidden_layers": 2,
|
| 30 |
-
"num_key_value_heads":
|
| 31 |
"query_pre_attn_scalar": 256,
|
| 32 |
"rms_norm_eps": 1e-06,
|
| 33 |
"rope_local_base_freq": 10000.0,
|
| 34 |
-
"rope_scaling":
|
|
|
|
|
|
|
|
|
|
| 35 |
"rope_theta": 1000000.0,
|
| 36 |
-
"sliding_window":
|
| 37 |
"use_cache": true,
|
| 38 |
-
"vocab_size":
|
| 39 |
},
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
"transformers_version": "4.56.0.dev0",
|
|
@@ -43,13 +82,14 @@
|
|
| 43 |
"attention_dropout": 0.0,
|
| 44 |
"hidden_act": "gelu_pytorch_tanh",
|
| 45 |
"hidden_size": 16,
|
| 46 |
-
"image_size":
|
| 47 |
-
"intermediate_size":
|
| 48 |
"layer_norm_eps": 1e-06,
|
| 49 |
"model_type": "siglip_vision_model",
|
| 50 |
-
"num_attention_heads":
|
| 51 |
"num_channels": 3,
|
| 52 |
"num_hidden_layers": 2,
|
| 53 |
-
"patch_size":
|
|
|
|
| 54 |
}
|
| 55 |
}
|
|
|
|
| 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,
|
|
|
|
| 22 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 23 |
"hidden_size": 16,
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 10240,
|
| 26 |
"layer_types": [
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
"sliding_attention",
|
| 60 |
"sliding_attention"
|
| 61 |
],
|
| 62 |
"max_position_embeddings": 131072,
|
| 63 |
"model_type": "gemma3_text",
|
| 64 |
+
"num_attention_heads": 8,
|
| 65 |
"num_hidden_layers": 2,
|
| 66 |
+
"num_key_value_heads": 4,
|
| 67 |
"query_pre_attn_scalar": 256,
|
| 68 |
"rms_norm_eps": 1e-06,
|
| 69 |
"rope_local_base_freq": 10000.0,
|
| 70 |
+
"rope_scaling": {
|
| 71 |
+
"factor": 8.0,
|
| 72 |
+
"rope_type": "linear"
|
| 73 |
+
},
|
| 74 |
"rope_theta": 1000000.0,
|
| 75 |
+
"sliding_window": 1024,
|
| 76 |
"use_cache": true,
|
| 77 |
+
"vocab_size": 262208
|
| 78 |
},
|
| 79 |
"torch_dtype": "float32",
|
| 80 |
"transformers_version": "4.56.0.dev0",
|
|
|
|
| 82 |
"attention_dropout": 0.0,
|
| 83 |
"hidden_act": "gelu_pytorch_tanh",
|
| 84 |
"hidden_size": 16,
|
| 85 |
+
"image_size": 896,
|
| 86 |
+
"intermediate_size": 4304,
|
| 87 |
"layer_norm_eps": 1e-06,
|
| 88 |
"model_type": "siglip_vision_model",
|
| 89 |
+
"num_attention_heads": 16,
|
| 90 |
"num_channels": 3,
|
| 91 |
"num_hidden_layers": 2,
|
| 92 |
+
"patch_size": 14,
|
| 93 |
+
"vision_use_head": false
|
| 94 |
}
|
| 95 |
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
|
| 5 |
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.56.0.dev0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106
|
| 7 |
+
],
|
| 8 |
"pad_token_id": 0,
|
| 9 |
"transformers_version": "4.56.0.dev0"
|
| 10 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db80e8136185f45ba7732fd1f88b0fc7446ff8169fafdded5cdf9f57a7303b70
|
| 3 |
+
size 22959728
|