Nitzanbanin commited on
Commit
20554e2
ยท
verified ยท
1 Parent(s): 3bae3c8

Upload project components after file path verification and unification

Browse files
Files changed (1) hide show
  1. README.md +4 -81
README.md CHANGED
@@ -1,81 +1,4 @@
1
- ---
2
- license: mit
3
- language:
4
- - he
5
- tags:
6
- - hebrew
7
- - nlp
8
- - morphological-analysis
9
- - root-analysis
10
- - json
11
- pipeline_tag: text-generation
12
- ---
13
-
14
- <div dir="rtl">
15
-
16
- # Davar-IvriNet
17
-
18
- **Davar-IvriNet** ื”ื•ื ืžื•ื“ืœ ืฉืคื” ืฉืคื•ืชื— ื•ืื•ืžืŸ ื‘ืžื™ื•ื—ื“ ื›ื“ื™ ืœืฉืžืฉ ื›ืžื ื•ืข ืœื ื™ืชื•ื— ืžื•ืจืคื•ืœื•ื’ื™ ืขืฉื™ืจ ื•ืžืขืžื™ืง ืฉืœ ื”ืฉืคื” ื”ืขื‘ืจื™ืช. ื”ืžื•ื“ืœ ืžื”ื•ื•ื” ืืช ืœื™ื‘ืช ื”ื™ื“ืข ืฉืœ ืคืจื•ื™ืงื˜ **[ื“ึธึผื‘ึธืจ](https://github.com/nitzan-gimmi/Davar)**, ืคืจื•ื™ืงื˜ ืงื•ื“ ืคืชื•ื— ืฉืžื˜ืจืชื• ืœื‘ื ื•ืช ืชืฉืชื™ืช ื™ื“ืข ื•ื›ืœื™ื ืœืžืคืชื—ื™ื, ื‘ืœืฉื ื™ื ื•ื—ื•ืงืจื™ AI ื”ืขื•ืกืงื™ื ื‘ืขื‘ืจื™ืช.
19
-
20
- ## ื—ื–ื•ืŸ ื•ืžื˜ืจื”
21
-
22
- ื”ืฉืคื” ื”ืขื‘ืจื™ืช, ืขืœ ื”ืžื•ืจืคื•ืœื•ื’ื™ื” ื”ืขืฉื™ืจื” ื•ื”ื›ืชื™ื‘ ื”ื—ืกืจ (ืœืœื ื ื™ืงื•ื“), ืžืฆื™ื‘ื” ืืชื’ืจื™ื ืžืฉืžืขื•ืชื™ื™ื ืœืžืขืจื›ื•ืช ืขื™ื‘ื•ื“ ืฉืคื” ื˜ื‘ืขื™ืช (NLP). ืžื•ื“ืœื™ื ื›ืœืœื™ื™ื ืžืชืงืฉื™ื ืœืขื™ืชื™ื ืงืจื•ื‘ื•ืช ืœืคืขื ื— ืืช ื”ืžื‘ื ื” ื”ื ื›ื•ืŸ ืฉืœ ืžื™ืœื”, ืืช ื”ื‘ื ื™ื™ืŸ, ื”ื’ื–ืจื”, ืื• ืืคื™ืœื• ืืช ื”ื”ื’ื™ื™ื” ื”ืžื“ื•ื™ืงืช.
23
-
24
- **Davar-IvriNet** ื ื•ืขื“ ืœืคืชื•ืจ ื‘ืขื™ื” ื–ื•. ื‘ืžืงื•ื ืœื”ืกืชืžืš ืขืœ ื”ื ื—ื™ื•ืช ืžื•ืจื›ื‘ื•ืช ืœืžื•ื“ืœื™ ืฉืคื” ื›ืœืœื™ื™ื, ื”ื•ื ืื•ืžืŸ ื‘ืื•ืคืŸ ื™ื™ืขื•ื“ื™ ืœืกืคืง ื ื™ืชื•ื— ืžื•ืจืคื•ืœื•ื’ื™ ืžืœื ื•ืขืฉื™ืจ, ื”ืžื‘ื•ืกืก ืขืœ ืฉื•ืจืฉ ื”ืžื™ืœื”. ื”ื•ื ืžืงื‘ืœ ื›ืงืœื˜ ืฉื•ืจืฉ ื‘ืขื‘ืจื™ืช ื•ืžื—ื–ื™ืจ ืžืขืจืš ืฉืœ ืื•ื‘ื™ื™ืงื˜ื™ JSON, ื›ืืฉืจ ื›ืœ ืื•ื‘ื™ื™ืงื˜ ืžื™ื™ืฆื’ ื”ื˜ื™ื” ืื• ืžื™ืœื” ื ื’ื–ืจืช, ื•ืžื›ื™ืœ ื ื™ืชื•ื— ืžืคื•ืจื˜ ืขืœ ืคื™ ืกื›ื™ืžื” ืขืฉื™ืจื”.
25
-
26
- ## ืืจื›ื™ื˜ืงื˜ื•ืจืช ื”ืคืจื•ื™ืงื˜
27
-
28
- ื”ืžื•ื“ืœ ื”ื–ื” ืื™ื ื• ืขื•ืžื“ ื‘ืคื ื™ ืขืฆืžื•. ื”ื•ื ืžื”ื•ื•ื” ืืช ื”"ืžื•ื—" ื”ืžื•ืžื—ื” ื‘ืชื•ืš ืืจื›ื™ื˜ืงื˜ื•ืจื” ื’ื“ื•ืœื” ื™ื•ืชืจ, ื”ื›ื•ืœืœืช ื’ื ืžืžืฉืง ืžืฉืชืžืฉ:
29
-
30
- * **ื”ืืคืœื™ืงืฆื™ื” (ื”ืฆืจื›ืŸ):** [ื›ืืŸ ื ื™ืชืŸ ืœื”ื•ืกื™ืฃ ืงื™ืฉื•ืจ ืœืืคืœื™ืงืฆื™ื” ื”ื—ื™ื”] ื”ื™ื ืžืžืฉืง ื”-Web ืฉื“ืจื›ื• ืžืฉืชืžืฉื™ื ื™ื›ื•ืœื™ื ืœื”ื›ื ื™ืก ืฉื•ืจืฉ ื•ืœืงื‘ืœ ืืช ื”ื ื™ืชื•ื— ื”ืžืœื. ืžืžืฉืง ื–ื” ื‘ื ื•ื™ ื‘-Next.js ื•-React.
31
- * **ืžื ื•ืข ื”-AI (ื”ืžืชื•ื•ืš):** ืžื ื•ืข ืžื‘ื•ืกืก Genkit ืฉืžืฉืžืฉ ื›"ืžื ื”ืœ ืชื–ืžื•ืจืช". ื”ื•ื ืžืงื‘ืœ ืืช ื”ื‘ืงืฉื” ืžื”ืžืžืฉืง, ื•ืžืคืขื™ืœ ืืช ื”ื›ืœื™ ื”ืžืชืื™ื.
32
- * **ื”ืžื•ื“ืœ (ื”ืกืคืง):** ื”ืžื•ื“ืœ ื”ื–ื”, `Davar-IvriNet`, ื”ื•ื "ื”ื›ืœื™ ื”ืžื•ืžื—ื”". ื”ื•ื ืžืงื‘ืœ ื‘ืงืฉื•ืช API ืžืžื ื•ืข ื”-AI ื•ืžืกืคืง ืืช ื”ื ื™ืชื•ื— ื”ืœื™ื ื’ื•ื•ื™ืกื˜ื™ ื”ืžื“ื•ื™ืง.
33
-
34
- ื”ื”ืคืจื“ื” ื”ื–ื• ืžืืคืฉืจืช ื’ืžื™ืฉื•ืช ืžื™ืจื‘ื™ืช. ื”ืืคืœื™ืงืฆื™ื” ื™ื›ื•ืœื” ืœื”ืชืคืชื— ื•ืœื”ืฉืชื ื•ืช, ื‘ื–ืžืŸ ืฉื”ืžื•ื“ืœ ื ืฉืืจ ืžืงื•ืจ ื”ื™ื“ืข ื”ืžืจื›ื–ื™ ื•ื”ืืžื™ืŸ.
35
-
36
- ## ืกื›ื™ืžืช ื”ื ืชื•ื ื™ื (Schema)
37
-
38
- ื›ืœ ืจืฉื•ืžืช JSON ืฉื”ืžื•ื“ืœ ืžื—ื–ื™ืจ ื‘ื ื•ื™ื” ืขืœ ืคื™ ื”ืกื›ื™ืžื” ื”ืžืคื•ืจื˜ืช ื”ื‘ืื”, ื”ื›ื•ืœืœืช 20 ืฉื“ื•ืช ื”ืžืกืคืงื™ื ื ื™ืชื•ื— ืžืงื™ืฃ:
39
-
40
- | ืฉื“ื” | ืชื™ืื•ืจ | ื“ื•ื’ืžื” (ืขื‘ื•ืจ "ืฉึธืืžึทืจึฐืชึดึผื™") |
41
- | :--- | :--- | :--- |
42
- | `root` | ื”ืฉื•ืจืฉ ื”ืขื‘ืจื™. | `ืฉ-ืž-ืจ` |
43
- | `gzera` | ื”ื’ื–ืจื” ืฉืœ ื”ืฉื•ืจืฉ. | `ืฉืœืžื™ื` |
44
- | `binyan` | ื‘ื ื™ื™ืŸ ื”ืคื•ืขืœ. | `paal` |
45
- | `lemma` | ืฆื•ืจืช ื”ืžืงื•ืจ ืฉืœ ื”ืคื•ืขืœ. | `ืฉึธืืžึทืจ` |
46
- | `voice` | ื”ืงื•ืœ ื”ื“ืงื“ื•ืงื™. | `active` |
47
- | `tense` | ื”ื–ืžืŸ ื”ื“ืงื“ื•ืงื™. | `past` |
48
- | `person` | ื”ื’ื•ืฃ ื”ื“ืงื“ื•ืงื™. | `1s` (ื’ื•ืฃ ืจืืฉื•ืŸ, ื™ื—ื™ื“) |
49
- | `form` | ื”ืฆื•ืจื” ื”ืžืœืื” ื•ื”ืžื ื•ืงื“ืช. | `ืฉึธืืžึทืจึฐืชึดึผื™` |
50
- | `infinitive` | ืฉื ื”ืคื•ืขืœ. | `ืœืฉืžื•ืจ` |
51
- | `meaning_he` | ืžืฉืžืขื•ืช ื‘ืขื‘ืจื™ืช. | `ืœืฉืžื•ืจ` |
52
- | `meaning_en` | ืžืฉืžืขื•ืช ื‘ืื ื’ืœื™ืช. | `to guard` |
53
- | `nikud` | ืฆื•ืจืช ืฉื ื”ืคื•ืขืœ ืขื ื ื™ืงื•ื“. | `ืœึดืฉึฐืืžึนืจ` |
54
- | `tokens` | ืคื™ืจื•ืง ื”ืžื™ืœื” ืœืžื•ืจืคืžื•ืช. | `[{"type": "root", "value": "ืฉืžืจ"}, {"type": "suffix", "value": "ืชื™"}]` |
55
- | `ipa` | ืชืขืชื™ืง ืคื•ื ื˜ื™ ื‘ื™ื ืœืื•ืžื™. | `/สƒaหˆmaสti/` |
56
- | `ipa_teacher` | ืชืขืชื™ืง IPA ืœื™ืžื•ื“ื™/ื—ืœื•ืคื™. | `sha-MAR-ti` |
57
- | `dictionary_form`| ืฉื ื”ืคืขื•ืœื”. | `ืฉึฐืืžึดื™ืจึธื”` |
58
-
59
- ## ืื™ืš ืœื”ืฉืชืžืฉ ื‘ืžื•ื“ืœ? (ื“ืจืš ื”-API)
60
-
61
- ื ื™ืชืŸ ืœืงืจื•ื ืœืžื•ื“ืœ ื‘ืืžืฆืขื•ืช ื”-Inference API ืฉืœ Hugging Face. ื™ืฉ ืœืฉืœื•ื— ื‘ืงืฉืช `POST` ืœื›ืชื•ื‘ืช ื”-API ืฉืœ ื”ืžื•ื“ืœ, ืขื ื”ื˜ื•ืงืŸ ืฉืœื›ื.
62
-
63
- ืœื”ืœืŸ ื“ื•ื’ืžืช ืงื•ื“ ื‘-JavaScript ื”ืžื“ื’ื™ืžื” ืื™ืš ืœืงืจื•ื ืœืžื•ื“ืœ ืขื ื”ืฉื•ืจืฉ "ื›-ืช-ื‘":
64
-
65
- ```javascript
66
- async function query(data) {
67
- const response = await fetch(
68
- "https://api-inference.huggingface.co/models/Nitzanbanin/Davar-IvriNet",
69
- {
70
- headers: { Authorization: "Bearer YOUR_HUGGINGFACE_TOKEN" }, // ื”ื—ืœื™ืคื• ื‘ื˜ื•ืงืŸ ืฉืœื›ื
71
- method: "POST",
72
- body: JSON.stringify(data),
73
- }
74
- );
75
- const result = await response.json();
76
- return result;
77
- }
78
-
79
- query({ "inputs": "ื›-ืช-ื‘" }).then((response) => {
80
- console.log(JSON.stringify(response, null, 2));
81
- });
 
1
+ # ื“ึธึผื‘ึธืจ โ€“ ืžื•ื“ืœ ื™ื“ืข ื•ืชื•ื›ื ื™๏ฟฝ๏ฟฝ ืœื™ืžื•ื“ื™ื ืœืขื‘ืจื™ืช
2
+ Davar โ€“ Open Hebrew Language Knowledge Model & Curriculum
3
+ ยฉ 2025 โ€“ ื ึดืฆืŸ ื‘ึผึฐื ึดื™ืŸ & Google Gemini
4
+ License: MIT