Hayme commited on
Commit
1058225
·
verified ·
1 Parent(s): 6a4245f

Upload AgriSagot Philippine agricultural BERT model

Browse files
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - agriculture
4
+ - bert
5
+ - philippine-agriculture
6
+ - crop-disease
7
+ - recommendation
8
+ - agrisagot
9
+ language:
10
+ - en
11
+ license: mit
12
+ ---
13
+
14
+ # AgriSagot BERT - Philippine Agricultural Recommender
15
+
16
+ This model is fine-tuned on Philippine agricultural data for crop disease and pesticide recommendations, specifically designed for the AgriSagot application.
17
+
18
+ ## Model Description
19
+
20
+ - **Base Model**: BERT-base-uncased
21
+ - **Training Data**: Philippine registered agricultural products (as of August 2025)
22
+ - **Use Case**: Agricultural product recommendations based on crop and disease
23
+ - **Language**: English
24
+ - **Country**: Philippines
25
+ - **Application**: AgriSagot - Smart Agricultural Advisory System
26
+
27
+ ## Usage
28
+
29
+ ```python
30
+ from transformers import AutoModel, AutoTokenizer
31
+
32
+ model = AutoModel.from_pretrained("Hayme/agrisago-bert")
33
+ tokenizer = AutoTokenizer.from_pretrained("Hayme/agrisago-bert")
34
+
35
+ # Use for generating embeddings
36
+ inputs = tokenizer("rice blast treatment", return_tensors="pt")
37
+ outputs = model(**inputs)
38
+ embeddings = outputs.last_hidden_state.mean(dim=1)
39
+ ```
40
+
41
+ ## API Usage
42
+
43
+ ```javascript
44
+ // In your AgriSagot API
45
+ const response = await hf.featureExtraction({
46
+ model: 'Hayme/agrisago-bert',
47
+ inputs: 'rice brown planthopper treatment'
48
+ });
49
+ ```
50
+
51
+ ## Training Data
52
+
53
+ Trained on the official "UPDATED LIST OF REGISTERED PRODUCTS As of August 31, 2025" from Philippine regulatory authorities, containing comprehensive information about:
54
+
55
+ - Agricultural pesticides
56
+ - Fertilizers
57
+ - Plant growth regulators
58
+ - Crop protection products
59
+ - Target crops and pests/diseases
60
+ - Active ingredients and formulations
61
+
62
+ ## Intended Use
63
+
64
+ - Crop disease identification and treatment recommendations
65
+ - Agricultural product recommendations for Philippine farmers
66
+ - Pesticide matching for specific crop-disease combinations
67
+ - Integration with AgriSagot mobile and web applications
68
+ - Philippine agricultural advisory and extension services
69
+
70
+ ## Performance
71
+
72
+ This model understands Philippine-specific agricultural contexts including:
73
+ - Local crop varieties (rice, corn, tomato, etc.)
74
+ - Common Philippine pests and diseases
75
+ - Available agricultural products in the Philippine market
76
+ - Regulatory-approved treatment options
77
+
78
+ ## Limitations
79
+
80
+ - Trained specifically on Philippine agricultural data
81
+ - Recommendations should be verified with local agricultural experts
82
+ - Not suitable for other countries' agricultural systems without adaptation
83
+
84
+ ## Citation
85
+
86
+ If you use this model, please cite:
87
+ ```
88
+ AgriSagot BERT Model (2025)
89
+ Trained on Philippine Agricultural Product Database
90
+ Available at: https://huggingface.co/Hayme/agrisago-bert
91
+ ```
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.57.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019aa07f3b343bd542efdf5b843a91d764fc03bd49ef07db870f13be5164bd21
3
+ size 437951328
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff