update the space link
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ tags:
|
|
9 |
- BhabhaAI/Gajendra-v0.1
|
10 |
---
|
11 |
|
12 |
-
# yuj-v1
|
13 |
|
14 |
The yuj-v1 model is a blend of advanced models strategically crafted to enhance Hindi Language Models (LLMs) effectively and democratically. Its primary goals include catalyzing the development of Hindi and its communities, making significant contributions to linguistic knowledge. The term "yuj," from Sanskrit, signifies fundamental unity, highlighting the integration of sophisticated technologies to improve the language experience for users in the Hindi-speaking community.
|
15 |
|
@@ -19,28 +19,12 @@ Below are the model which are leverage to build this yuj-v1:
|
|
19 |
* [ai4bharat/Airavata](https://huggingface.co/ai4bharat/Airavata)
|
20 |
* [BhabhaAI/Gajendra-v0.1](https://huggingface.co/BhabhaAI/Gajendra-v0.1)
|
21 |
|
22 |
-
##
|
23 |
|
24 |
-
|
25 |
-
models:
|
26 |
-
- model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
|
27 |
-
# no parameters necessary for base model
|
28 |
-
- model: ai4bharat/Airavata
|
29 |
-
parameters:
|
30 |
-
density: 0.5
|
31 |
-
weight: 0.5
|
32 |
-
- model: BhabhaAI/Gajendra-v0.1
|
33 |
-
parameters:
|
34 |
-
density: 0.5
|
35 |
-
weight: 0.3
|
36 |
-
merge_method: ties
|
37 |
-
base_model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
|
38 |
-
parameters:
|
39 |
-
normalize: true
|
40 |
-
dtype: float16
|
41 |
-
```
|
42 |
|
43 |
-
|
|
|
44 |
|
45 |
First, you need to install some of below packages:
|
46 |
|
@@ -76,10 +60,25 @@ tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokeniza
|
|
76 |
युज शीर्ष द्विभाषी मॉडल में से एक है। यह एक उत्पादक मॉडल है जो एक साथ एक ट्रांसफॉर्मर और एक आत्म-ध्यान तंत्रिका नेटवर्क को जोड़ता है। यह एक ट्रांसफॉर्मर वास्तुकला का उपयोग करता है जो एक ट्रांसफॉर्मर मॉडल की तुलना में बहुत अधिक जटिल है।
|
77 |
```
|
78 |
|
79 |
-
##
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
- BhabhaAI/Gajendra-v0.1
|
10 |
---
|
11 |
|
12 |
+
# The Model yuj-v1:
|
13 |
|
14 |
The yuj-v1 model is a blend of advanced models strategically crafted to enhance Hindi Language Models (LLMs) effectively and democratically. Its primary goals include catalyzing the development of Hindi and its communities, making significant contributions to linguistic knowledge. The term "yuj," from Sanskrit, signifies fundamental unity, highlighting the integration of sophisticated technologies to improve the language experience for users in the Hindi-speaking community.
|
15 |
|
|
|
19 |
* [ai4bharat/Airavata](https://huggingface.co/ai4bharat/Airavata)
|
20 |
* [BhabhaAI/Gajendra-v0.1](https://huggingface.co/BhabhaAI/Gajendra-v0.1)
|
21 |
|
22 |
+
## ☄️Space to use it:
|
23 |
|
24 |
+
[**yuj-v1 tryO**](https://shuvom-yuj-v1-tryo.hf.space)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
+
|
27 |
+
## 💻 Usage:
|
28 |
|
29 |
First, you need to install some of below packages:
|
30 |
|
|
|
60 |
युज शीर्ष द्विभाषी मॉडल में से एक है। यह एक उत्पादक मॉडल है जो एक साथ एक ट्रांसफॉर्मर और एक आत्म-ध्यान तंत्रिका नेटवर्क को जोड़ता है। यह एक ट्रांसफॉर्मर वास्तुकला का उपयोग करता है जो एक ट्रांसफॉर्मर मॉडल की तुलना में बहुत अधिक जटिल है।
|
61 |
```
|
62 |
|
63 |
+
## 🧩 Configuration
|
64 |
+
|
65 |
+
```yaml
|
66 |
+
models:
|
67 |
+
- model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
|
68 |
+
# no parameters necessary for base model
|
69 |
+
- model: ai4bharat/Airavata
|
70 |
+
parameters:
|
71 |
+
density: 0.5
|
72 |
+
weight: 0.5
|
73 |
+
- model: BhabhaAI/Gajendra-v0.1
|
74 |
+
parameters:
|
75 |
+
density: 0.5
|
76 |
+
weight: 0.3
|
77 |
+
merge_method: ties
|
78 |
+
base_model: sarvamai/OpenHathi-7B-Hi-v0.1-Base
|
79 |
+
parameters:
|
80 |
+
normalize: true
|
81 |
+
dtype: float16
|
82 |
+
```
|
83 |
+
|
84 |
+
|