Upload VisionPixtralEncoderDecoder
Browse files- config.json +4 -14
- generation_config.json +3 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -2,20 +2,13 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"VisionPixtralEncoderDecoder"
|
| 4 |
],
|
| 5 |
-
"auto_map": {
|
| 6 |
-
"AutoConfig": "configuration.VisionPixtralEncoderDecoderConfig",
|
| 7 |
-
"AutoModel": "modeling.VisionPixtralEncoderDecoder",
|
| 8 |
-
"AutoConfig": "configuration.PixtralVisionModelBatchConfig",
|
| 9 |
-
"AutoModel": "modeling.PixtralVisionModelBatch"
|
| 10 |
-
},
|
| 11 |
"decoder": {
|
| 12 |
-
"_attn_implementation_autoset": true,
|
| 13 |
"activation_dropout": 0.0,
|
| 14 |
"activation_function": "relu",
|
| 15 |
"add_cross_attention": true,
|
| 16 |
"attention_dropout": 0.0,
|
| 17 |
"classifier_dropout": 0.0,
|
| 18 |
-
"cross_attention_hidden_size":
|
| 19 |
"d_model": 1024,
|
| 20 |
"decoder_attention_heads": 16,
|
| 21 |
"decoder_ffn_dim": 4096,
|
|
@@ -36,13 +29,10 @@
|
|
| 36 |
},
|
| 37 |
"encoder": {
|
| 38 |
"_attn_implementation_autoset": true,
|
|
|
|
| 39 |
"architectures": [
|
| 40 |
-
"
|
| 41 |
],
|
| 42 |
-
"auto_map": {
|
| 43 |
-
"AutoConfig": "configuration.PixtralVisionModelBatchConfig",
|
| 44 |
-
"AutoModel": "modeling.PixtralVisionModelBatch"
|
| 45 |
-
},
|
| 46 |
"attention_dropout": 0.0,
|
| 47 |
"head_dim": 64,
|
| 48 |
"hidden_act": "silu",
|
|
@@ -61,7 +51,7 @@
|
|
| 61 |
"torch_dtype": "float32"
|
| 62 |
},
|
| 63 |
"is_encoder_decoder": true,
|
| 64 |
-
"model_type": "
|
| 65 |
"tie_word_embeddings": false,
|
| 66 |
"torch_dtype": "float32",
|
| 67 |
"transformers_version": "4.51.3"
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"VisionPixtralEncoderDecoder"
|
| 4 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"decoder": {
|
|
|
|
| 6 |
"activation_dropout": 0.0,
|
| 7 |
"activation_function": "relu",
|
| 8 |
"add_cross_attention": true,
|
| 9 |
"attention_dropout": 0.0,
|
| 10 |
"classifier_dropout": 0.0,
|
| 11 |
+
"cross_attention_hidden_size": 768,
|
| 12 |
"d_model": 1024,
|
| 13 |
"decoder_attention_heads": 16,
|
| 14 |
"decoder_ffn_dim": 4096,
|
|
|
|
| 29 |
},
|
| 30 |
"encoder": {
|
| 31 |
"_attn_implementation_autoset": true,
|
| 32 |
+
"_name_or_path": "pixtral-vision",
|
| 33 |
"architectures": [
|
| 34 |
+
"PixtralVisionModel"
|
| 35 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"attention_dropout": 0.0,
|
| 37 |
"head_dim": 64,
|
| 38 |
"hidden_act": "silu",
|
|
|
|
| 51 |
"torch_dtype": "float32"
|
| 52 |
},
|
| 53 |
"is_encoder_decoder": true,
|
| 54 |
+
"model_type": "vision-encoder-decoder",
|
| 55 |
"tie_word_embeddings": false,
|
| 56 |
"torch_dtype": "float32",
|
| 57 |
"transformers_version": "4.51.3"
|
generation_config.json
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
-
"decoder_start_token_id":
|
| 5 |
"eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
-
"transformers_version": "4.51.3"
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
"eos_token_id": 2,
|
| 6 |
"pad_token_id": 1,
|
| 7 |
+
"transformers_version": "4.51.3",
|
| 8 |
+
"use_cache": false
|
| 9 |
}
|
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 sha256:46d0f12a41becf763629a128b3310725829fd63f8f8420568bdee03bafb28edb
|
| 3 |
+
size 2810021492
|