Training in progress, step 50
Browse files- config.json +63 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GitForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 101,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 102,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 1024,
|
| 17 |
+
"model_type": "git",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"num_image_with_embedding": null,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"transformers_version": "5.2.0",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vision_config": {
|
| 27 |
+
"add_cross_attention": false,
|
| 28 |
+
"attention_dropout": 0.0,
|
| 29 |
+
"bos_token_id": null,
|
| 30 |
+
"cross_attention_hidden_size": null,
|
| 31 |
+
"decoder_start_token_id": null,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dtype": "float32",
|
| 34 |
+
"eos_token_id": null,
|
| 35 |
+
"finetuning_task": null,
|
| 36 |
+
"hidden_act": "quick_gelu",
|
| 37 |
+
"hidden_size": 768,
|
| 38 |
+
"image_size": 224,
|
| 39 |
+
"initializer_factor": 1.0,
|
| 40 |
+
"initializer_range": 0.02,
|
| 41 |
+
"intermediate_size": 3072,
|
| 42 |
+
"is_decoder": false,
|
| 43 |
+
"layer_norm_eps": 1e-05,
|
| 44 |
+
"model_type": "git_vision_model",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_channels": 3,
|
| 47 |
+
"num_hidden_layers": 12,
|
| 48 |
+
"pad_token_id": null,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"prefix": null,
|
| 51 |
+
"projection_dim": 512,
|
| 52 |
+
"pruned_heads": {},
|
| 53 |
+
"sep_token_id": null,
|
| 54 |
+
"task_specific_params": null,
|
| 55 |
+
"tf_legacy_loss": false,
|
| 56 |
+
"tie_encoder_decoder": false,
|
| 57 |
+
"tie_word_embeddings": true,
|
| 58 |
+
"tokenizer_class": null,
|
| 59 |
+
"torchscript": false,
|
| 60 |
+
"use_bfloat16": false
|
| 61 |
+
},
|
| 62 |
+
"vocab_size": 30522
|
| 63 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 101,
|
| 4 |
+
"eos_token_id": 102,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.2.0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e61aa4a60b8a312b83e897c35125ffce5a0510fe19777d704f70276013c70e95
|
| 3 |
+
size 706516024
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84e94af056dcb0ed6ceaa84806640016af03f2a6719e2fe1f459d3d383af8a32
|
| 3 |
+
size 4792
|