Upload model
Browse files- config.json +77 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VisionEncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_attn_implementation_autoset": true,
|
| 7 |
+
"_name_or_path": "gpt2",
|
| 8 |
+
"activation_function": "gelu_new",
|
| 9 |
+
"add_cross_attention": true,
|
| 10 |
+
"architectures": [
|
| 11 |
+
"GPT2LMHeadModel"
|
| 12 |
+
],
|
| 13 |
+
"attn_pdrop": 0.1,
|
| 14 |
+
"embd_pdrop": 0.1,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"is_decoder": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-05,
|
| 18 |
+
"model_type": "gpt2",
|
| 19 |
+
"n_ctx": 1024,
|
| 20 |
+
"n_embd": 768,
|
| 21 |
+
"n_head": 12,
|
| 22 |
+
"n_inner": null,
|
| 23 |
+
"n_layer": 12,
|
| 24 |
+
"n_positions": 1024,
|
| 25 |
+
"reorder_and_upcast_attn": false,
|
| 26 |
+
"resid_pdrop": 0.1,
|
| 27 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 28 |
+
"scale_attn_weights": true,
|
| 29 |
+
"summary_activation": null,
|
| 30 |
+
"summary_first_dropout": 0.1,
|
| 31 |
+
"summary_proj_to_labels": true,
|
| 32 |
+
"summary_type": "cls_index",
|
| 33 |
+
"summary_use_proj": true,
|
| 34 |
+
"task_specific_params": {
|
| 35 |
+
"text-generation": {
|
| 36 |
+
"do_sample": true,
|
| 37 |
+
"max_length": 50
|
| 38 |
+
}
|
| 39 |
+
},
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
},
|
| 44 |
+
"decoder_start_token_id": 50256,
|
| 45 |
+
"encoder": {
|
| 46 |
+
"_attn_implementation_autoset": true,
|
| 47 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 48 |
+
"architectures": [
|
| 49 |
+
"ViTModel"
|
| 50 |
+
],
|
| 51 |
+
"attention_probs_dropout_prob": 0.0,
|
| 52 |
+
"encoder_stride": 16,
|
| 53 |
+
"hidden_act": "gelu",
|
| 54 |
+
"hidden_dropout_prob": 0.0,
|
| 55 |
+
"hidden_size": 768,
|
| 56 |
+
"image_size": 224,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"intermediate_size": 3072,
|
| 59 |
+
"layer_norm_eps": 1e-12,
|
| 60 |
+
"model_type": "vit",
|
| 61 |
+
"num_attention_heads": 12,
|
| 62 |
+
"num_channels": 3,
|
| 63 |
+
"num_hidden_layers": 12,
|
| 64 |
+
"patch_size": 16,
|
| 65 |
+
"pooler_act": "tanh",
|
| 66 |
+
"pooler_output_size": 768,
|
| 67 |
+
"qkv_bias": true,
|
| 68 |
+
"torch_dtype": "float32"
|
| 69 |
+
},
|
| 70 |
+
"eos_token_id": 50256,
|
| 71 |
+
"is_encoder_decoder": true,
|
| 72 |
+
"model_type": "vision-encoder-decoder",
|
| 73 |
+
"pad_token_id": 50256,
|
| 74 |
+
"tie_word_embeddings": false,
|
| 75 |
+
"torch_dtype": "float32",
|
| 76 |
+
"transformers_version": "4.50.2"
|
| 77 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.50.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2808a2e5c8601c6d4880151fb9d94f7b002a761c84fce70c77e917a0786bf97
|
| 3 |
+
size 956835520
|