Image-to-Text
Transformers
TensorBoard
Safetensors
English
git
image-text-to-text
Generated from Trainer
image-captioning
Instructions to use mrSoul7766/git-base-instagram-cap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mrSoul7766/git-base-instagram-cap with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="mrSoul7766/git-base-instagram-cap")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mrSoul7766/git-base-instagram-cap") model = AutoModelForMultimodalLM.from_pretrained("mrSoul7766/git-base-instagram-cap", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
a533918
1
Parent(s): 6557e1f
Training in progress, step 50
Browse files- README.md +2 -5
- config.json +4 -76
- model.safetensors +1 -1
- runs/Dec31_21-38-49_228ad310bd3c/events.out.tfevents.1704058742.228ad310bd3c.23033.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -6,9 +6,6 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: git-base-instagram-cap
|
| 8 |
results: []
|
| 9 |
-
pipeline_tag: image-to-text
|
| 10 |
-
language:
|
| 11 |
-
- en
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# git-base-instagram-cap
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.1859
|
| 22 |
- Wer Score: 1.0566
|
|
@@ -73,4 +70,4 @@ The following hyperparameters were used during training:
|
|
| 73 |
- Transformers 4.37.0.dev0
|
| 74 |
- Pytorch 2.1.0+cu121
|
| 75 |
- Datasets 2.16.1
|
| 76 |
-
- Tokenizers 0.15.0
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: git-base-instagram-cap
|
| 8 |
results: []
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 13 |
|
| 14 |
# git-base-instagram-cap
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.1859
|
| 19 |
- Wer Score: 1.0566
|
|
|
|
| 70 |
- Transformers 4.37.0.dev0
|
| 71 |
- Pytorch 2.1.0+cu121
|
| 72 |
- Datasets 2.16.1
|
| 73 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
"architectures": [
|
| 4 |
"GitForCausalLM"
|
| 5 |
],
|
|
@@ -22,85 +22,13 @@
|
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
-
"transformers_version":
|
| 26 |
"use_cache": true,
|
| 27 |
"vision_config": {
|
| 28 |
-
"_name_or_path": "",
|
| 29 |
-
"add_cross_attention": false,
|
| 30 |
-
"architectures": null,
|
| 31 |
-
"attention_dropout": 0.0,
|
| 32 |
-
"bad_words_ids": null,
|
| 33 |
-
"begin_suppress_tokens": null,
|
| 34 |
-
"bos_token_id": null,
|
| 35 |
-
"chunk_size_feed_forward": 0,
|
| 36 |
-
"cross_attention_hidden_size": null,
|
| 37 |
-
"decoder_start_token_id": null,
|
| 38 |
-
"diversity_penalty": 0.0,
|
| 39 |
-
"do_sample": false,
|
| 40 |
"dropout": 0.0,
|
| 41 |
-
"early_stopping": false,
|
| 42 |
-
"encoder_no_repeat_ngram_size": 0,
|
| 43 |
-
"eos_token_id": null,
|
| 44 |
-
"exponential_decay_length_penalty": null,
|
| 45 |
-
"finetuning_task": null,
|
| 46 |
-
"forced_bos_token_id": null,
|
| 47 |
-
"forced_eos_token_id": null,
|
| 48 |
-
"hidden_act": "quick_gelu",
|
| 49 |
-
"hidden_size": 768,
|
| 50 |
-
"id2label": {
|
| 51 |
-
"0": "LABEL_0",
|
| 52 |
-
"1": "LABEL_1"
|
| 53 |
-
},
|
| 54 |
-
"image_size": 224,
|
| 55 |
"initializer_factor": 1.0,
|
| 56 |
-
"initializer_range": 0.02,
|
| 57 |
-
"intermediate_size": 3072,
|
| 58 |
-
"is_decoder": false,
|
| 59 |
-
"is_encoder_decoder": false,
|
| 60 |
-
"label2id": {
|
| 61 |
-
"LABEL_0": 0,
|
| 62 |
-
"LABEL_1": 1
|
| 63 |
-
},
|
| 64 |
-
"layer_norm_eps": 1e-05,
|
| 65 |
-
"length_penalty": 1.0,
|
| 66 |
-
"max_length": 20,
|
| 67 |
-
"min_length": 0,
|
| 68 |
"model_type": "git_vision_model",
|
| 69 |
-
"
|
| 70 |
-
"num_attention_heads": 12,
|
| 71 |
-
"num_beam_groups": 1,
|
| 72 |
-
"num_beams": 1,
|
| 73 |
-
"num_channels": 3,
|
| 74 |
-
"num_hidden_layers": 12,
|
| 75 |
-
"num_return_sequences": 1,
|
| 76 |
-
"output_attentions": false,
|
| 77 |
-
"output_hidden_states": false,
|
| 78 |
-
"output_scores": false,
|
| 79 |
-
"pad_token_id": null,
|
| 80 |
-
"patch_size": 16,
|
| 81 |
-
"prefix": null,
|
| 82 |
-
"problem_type": null,
|
| 83 |
-
"projection_dim": 512,
|
| 84 |
-
"pruned_heads": {},
|
| 85 |
-
"remove_invalid_values": false,
|
| 86 |
-
"repetition_penalty": 1.0,
|
| 87 |
-
"return_dict": true,
|
| 88 |
-
"return_dict_in_generate": false,
|
| 89 |
-
"sep_token_id": null,
|
| 90 |
-
"suppress_tokens": null,
|
| 91 |
-
"task_specific_params": null,
|
| 92 |
-
"temperature": 1.0,
|
| 93 |
-
"tf_legacy_loss": false,
|
| 94 |
-
"tie_encoder_decoder": false,
|
| 95 |
-
"tie_word_embeddings": true,
|
| 96 |
-
"tokenizer_class": null,
|
| 97 |
-
"top_k": 50,
|
| 98 |
-
"top_p": 1.0,
|
| 99 |
-
"torch_dtype": null,
|
| 100 |
-
"torchscript": false,
|
| 101 |
-
"transformers_version": "4.26.0.dev0",
|
| 102 |
-
"typical_p": 1.0,
|
| 103 |
-
"use_bfloat16": false
|
| 104 |
},
|
| 105 |
"vocab_size": 30522
|
| 106 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/git-base",
|
| 3 |
"architectures": [
|
| 4 |
"GitForCausalLM"
|
| 5 |
],
|
|
|
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.37.0.dev0",
|
| 26 |
"use_cache": true,
|
| 27 |
"vision_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"initializer_factor": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"model_type": "git_vision_model",
|
| 31 |
+
"projection_dim": 512
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
},
|
| 33 |
"vocab_size": 30522
|
| 34 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 706516040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3de9541afdadfa55c1d95b83b44a0da0bacac2af4d40e3f5a08a412e83032d8
|
| 3 |
size 706516040
|
runs/Dec31_21-38-49_228ad310bd3c/events.out.tfevents.1704058742.228ad310bd3c.23033.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f306798b8794cc1e192fa3d6ef291ab67fef4cecf50362b17170f0e29a59dd2
|
| 3 |
+
size 5071
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:481560160e79d73d54389c0f78ef5b1dee3b592a93860c3af9d61d8ba74eb06a
|
| 3 |
size 4728
|