Upload config.json with huggingface_hub
Browse files- config.json +5 -18
config.json
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Mistral3ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"dtype": "bfloat16",
|
| 6 |
"image_token_index": 10,
|
| 7 |
"model_type": "mistral3",
|
| 8 |
"multimodal_projector_bias": false,
|
|
@@ -10,9 +9,6 @@
|
|
| 10 |
"spatial_merge_size": 2,
|
| 11 |
"text_config": {
|
| 12 |
"attention_dropout": 0.0,
|
| 13 |
-
"bos_token_id": 1,
|
| 14 |
-
"dtype": "bfloat16",
|
| 15 |
-
"eos_token_id": 2,
|
| 16 |
"head_dim": 128,
|
| 17 |
"hidden_act": "silu",
|
| 18 |
"hidden_size": 5120,
|
|
@@ -23,22 +19,16 @@
|
|
| 23 |
"num_attention_heads": 32,
|
| 24 |
"num_hidden_layers": 40,
|
| 25 |
"num_key_value_heads": 8,
|
| 26 |
-
"pad_token_id": null,
|
| 27 |
"rms_norm_eps": 1e-05,
|
| 28 |
-
"
|
| 29 |
-
"rope_theta": 1000000000.0,
|
| 30 |
-
"rope_type": "default"
|
| 31 |
-
},
|
| 32 |
"sliding_window": null,
|
| 33 |
-
"tie_word_embeddings": false,
|
| 34 |
"use_cache": true,
|
| 35 |
"vocab_size": 131072
|
| 36 |
},
|
| 37 |
-
"
|
| 38 |
-
"transformers_version": "
|
| 39 |
"vision_config": {
|
| 40 |
"attention_dropout": 0.0,
|
| 41 |
-
"dtype": "bfloat16",
|
| 42 |
"head_dim": 64,
|
| 43 |
"hidden_act": "silu",
|
| 44 |
"hidden_size": 1024,
|
|
@@ -50,10 +40,7 @@
|
|
| 50 |
"num_channels": 3,
|
| 51 |
"num_hidden_layers": 24,
|
| 52 |
"patch_size": 14,
|
| 53 |
-
"
|
| 54 |
-
"rope_theta": 10000.0,
|
| 55 |
-
"rope_type": "default"
|
| 56 |
-
}
|
| 57 |
},
|
| 58 |
"vision_feature_layer": -1
|
| 59 |
-
}
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Mistral3ForConditionalGeneration"
|
| 4 |
],
|
|
|
|
| 5 |
"image_token_index": 10,
|
| 6 |
"model_type": "mistral3",
|
| 7 |
"multimodal_projector_bias": false,
|
|
|
|
| 9 |
"spatial_merge_size": 2,
|
| 10 |
"text_config": {
|
| 11 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
| 12 |
"head_dim": 128,
|
| 13 |
"hidden_act": "silu",
|
| 14 |
"hidden_size": 5120,
|
|
|
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 40,
|
| 21 |
"num_key_value_heads": 8,
|
|
|
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_theta": 1000000000.0,
|
|
|
|
|
|
|
|
|
|
| 24 |
"sliding_window": null,
|
|
|
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 131072
|
| 27 |
},
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
"vision_config": {
|
| 31 |
"attention_dropout": 0.0,
|
|
|
|
| 32 |
"head_dim": 64,
|
| 33 |
"hidden_act": "silu",
|
| 34 |
"hidden_size": 1024,
|
|
|
|
| 40 |
"num_channels": 3,
|
| 41 |
"num_hidden_layers": 24,
|
| 42 |
"patch_size": 14,
|
| 43 |
+
"rope_theta": 10000.0
|
|
|
|
|
|
|
|
|
|
| 44 |
},
|
| 45 |
"vision_feature_layer": -1
|
| 46 |
+
}
|