Upload MultiModel Small 229M checkpoint
Browse files- config.json +42 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vision": {
|
| 3 |
+
"image_size": 224,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"hidden_size": 768,
|
| 6 |
+
"num_hidden_layers": 12,
|
| 7 |
+
"num_attention_heads": 12,
|
| 8 |
+
"intermediate_size": 3072,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"layer_norm_eps": 1e-06,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"image_channels": 3
|
| 13 |
+
},
|
| 14 |
+
"text": {
|
| 15 |
+
"vocab_size": 50257,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"max_position_embeddings": 512,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"pad_token_id": 50256,
|
| 26 |
+
"bos_token_id": 50256,
|
| 27 |
+
"eos_token_id": 50256
|
| 28 |
+
},
|
| 29 |
+
"projection": {
|
| 30 |
+
"vision_hidden_size": 768,
|
| 31 |
+
"text_hidden_size": 768,
|
| 32 |
+
"projection_size": 768,
|
| 33 |
+
"num_layers": 2,
|
| 34 |
+
"activation": "gelu",
|
| 35 |
+
"dropout": 0.1
|
| 36 |
+
},
|
| 37 |
+
"image_token_id": 50257,
|
| 38 |
+
"pad_token_id": 50256,
|
| 39 |
+
"bos_token_id": 50256,
|
| 40 |
+
"eos_token_id": 50256,
|
| 41 |
+
"model_type": "multimodal-small-gpt2"
|
| 42 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29789316b8bc5dfc1201d059a2e5e6fa71f9afdb7aa25ae1ff050c7d6f71bf79
|
| 3 |
+
size 917364047
|