Upload Gemma3ForConditionalGeneration
Browse files- config.json +4 -4
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
CHANGED
|
@@ -3,6 +3,7 @@
|
|
| 3 |
"Gemma3ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"boi_token_index": 255999,
|
|
|
|
| 6 |
"eoi_token_index": 256000,
|
| 7 |
"eos_token_id": [
|
| 8 |
1,
|
|
@@ -32,6 +33,7 @@
|
|
| 32 |
"attention_bias": false,
|
| 33 |
"attention_dropout": 0.0,
|
| 34 |
"attn_logit_softcapping": null,
|
|
|
|
| 35 |
"final_logit_softcapping": null,
|
| 36 |
"head_dim": 256,
|
| 37 |
"hidden_activation": "gelu_pytorch_tanh",
|
|
@@ -102,14 +104,13 @@
|
|
| 102 |
},
|
| 103 |
"rope_theta": 1000000.0,
|
| 104 |
"sliding_window": 1024,
|
| 105 |
-
"torch_dtype": "bfloat16",
|
| 106 |
"use_cache": true,
|
| 107 |
"vocab_size": 262208
|
| 108 |
},
|
| 109 |
-
"
|
| 110 |
-
"transformers_version": "4.53.3",
|
| 111 |
"vision_config": {
|
| 112 |
"attention_dropout": 0.0,
|
|
|
|
| 113 |
"hidden_act": "gelu_pytorch_tanh",
|
| 114 |
"hidden_size": 1152,
|
| 115 |
"image_size": 896,
|
|
@@ -120,7 +121,6 @@
|
|
| 120 |
"num_channels": 3,
|
| 121 |
"num_hidden_layers": 27,
|
| 122 |
"patch_size": 14,
|
| 123 |
-
"torch_dtype": "bfloat16",
|
| 124 |
"vision_use_head": false
|
| 125 |
}
|
| 126 |
}
|
|
|
|
| 3 |
"Gemma3ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"boi_token_index": 255999,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
"eoi_token_index": 256000,
|
| 8 |
"eos_token_id": [
|
| 9 |
1,
|
|
|
|
| 33 |
"attention_bias": false,
|
| 34 |
"attention_dropout": 0.0,
|
| 35 |
"attn_logit_softcapping": null,
|
| 36 |
+
"dtype": "bfloat16",
|
| 37 |
"final_logit_softcapping": null,
|
| 38 |
"head_dim": 256,
|
| 39 |
"hidden_activation": "gelu_pytorch_tanh",
|
|
|
|
| 104 |
},
|
| 105 |
"rope_theta": 1000000.0,
|
| 106 |
"sliding_window": 1024,
|
|
|
|
| 107 |
"use_cache": true,
|
| 108 |
"vocab_size": 262208
|
| 109 |
},
|
| 110 |
+
"transformers_version": "4.56.1",
|
|
|
|
| 111 |
"vision_config": {
|
| 112 |
"attention_dropout": 0.0,
|
| 113 |
+
"dtype": "bfloat16",
|
| 114 |
"hidden_act": "gelu_pytorch_tanh",
|
| 115 |
"hidden_size": 1152,
|
| 116 |
"image_size": 896,
|
|
|
|
| 121 |
"num_channels": 3,
|
| 122 |
"num_hidden_layers": 27,
|
| 123 |
"patch_size": 14,
|
|
|
|
| 124 |
"vision_use_head": false
|
| 125 |
}
|
| 126 |
}
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"pad_token_id": 0,
|
| 10 |
"top_k": 64,
|
| 11 |
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "4.
|
| 13 |
}
|
|
|
|
| 9 |
"pad_token_id": 0,
|
| 10 |
"top_k": 64,
|
| 11 |
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.56.1"
|
| 13 |
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5578abd3c27241a31f21c13220f44a427b99f1c36564ac587670f3be990d4ffc
|
| 3 |
+
size 4992269027
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:790314e959098fdf65825d475a12c794cacbdffe6097f72a1d25c5720d3625c3
|
| 3 |
+
size 2806556175
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|