Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,8 @@ language:
|
|
6 |
- vi
|
7 |
pipeline_tag: text-generation
|
8 |
base_model: HuggingFaceH4/zephyr-7b-beta
|
|
|
|
|
9 |
---
|
10 |
|
11 |
# Model Card for Model ID
|
@@ -52,8 +54,6 @@ tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False
|
|
52 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
53 |
results = tokenizer.batch_decode(outputs)[0]
|
54 |
print(results)
|
55 |
-
|
56 |
-
# Output:
|
57 |
# Bệnh dịch hạch ở châu Âu do khuẩn gây ra là do khuẩn Yersinia pestis.
|
58 |
```
|
59 |
|
@@ -67,8 +67,6 @@ tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False
|
|
67 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
68 |
results = tokenizer.batch_decode(outputs)[0]
|
69 |
print(results)
|
70 |
-
|
71 |
-
# Output:
|
72 |
# Peristernia despecta là một loài ốc biển, là động vật thân mềm chân bụng sống ở biển trong họ Fasciolariidae.
|
73 |
# ...
|
74 |
```
|
@@ -83,8 +81,6 @@ tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False
|
|
83 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
84 |
results = tokenizer.batch_decode(outputs)[0]
|
85 |
print(results)
|
86 |
-
|
87 |
-
# Output:
|
88 |
# Yes, I have knowledge about Vietnam. Vietnam is a country in Southeast Asia, bordered by China to the north, Laos and Cambodia to the west, and the South China Sea to the east and south. Its capital city is Hanoi, and its largest city is Ho Chi Minh City (formerly known as Saigon). Vietnam has a population of approximately 100 million people and a diverse cultural heritage influenced by both Chinese and French colonialism. The country has a rich history, including periods of independence, colonization, and resistance, and has experienced significant economic growth in recent years.
|
89 |
```
|
90 |
|
@@ -98,11 +94,26 @@ tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False
|
|
98 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
99 |
results = tokenizer.batch_decode(outputs)[0]
|
100 |
print(results)
|
101 |
-
|
102 |
-
# Output
|
103 |
# This is Vietnamese language. Vietnamese is a language spoken mainly in Vietnam and by the Vietnamese diaspora in many other countries. The sentence you provided means "I love you more than you think." It's like you have more love for someone than they realize.
|
104 |
```
|
105 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
## More Information
|
107 |
|
108 |
Many thanks for
|
|
|
6 |
- vi
|
7 |
pipeline_tag: text-generation
|
8 |
base_model: HuggingFaceH4/zephyr-7b-beta
|
9 |
+
tags:
|
10 |
+
- ghost
|
11 |
---
|
12 |
|
13 |
# Model Card for Model ID
|
|
|
54 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
55 |
results = tokenizer.batch_decode(outputs)[0]
|
56 |
print(results)
|
|
|
|
|
57 |
# Bệnh dịch hạch ở châu Âu do khuẩn gây ra là do khuẩn Yersinia pestis.
|
58 |
```
|
59 |
|
|
|
67 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
68 |
results = tokenizer.batch_decode(outputs)[0]
|
69 |
print(results)
|
|
|
|
|
70 |
# Peristernia despecta là một loài ốc biển, là động vật thân mềm chân bụng sống ở biển trong họ Fasciolariidae.
|
71 |
# ...
|
72 |
```
|
|
|
81 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
82 |
results = tokenizer.batch_decode(outputs)[0]
|
83 |
print(results)
|
|
|
|
|
84 |
# Yes, I have knowledge about Vietnam. Vietnam is a country in Southeast Asia, bordered by China to the north, Laos and Cambodia to the west, and the South China Sea to the east and south. Its capital city is Hanoi, and its largest city is Ho Chi Minh City (formerly known as Saigon). Vietnam has a population of approximately 100 million people and a diverse cultural heritage influenced by both Chinese and French colonialism. The country has a rich history, including periods of independence, colonization, and resistance, and has experienced significant economic growth in recent years.
|
85 |
```
|
86 |
|
|
|
94 |
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
95 |
results = tokenizer.batch_decode(outputs)[0]
|
96 |
print(results)
|
|
|
|
|
97 |
# This is Vietnamese language. Vietnamese is a language spoken mainly in Vietnam and by the Vietnamese diaspora in many other countries. The sentence you provided means "I love you more than you think." It's like you have more love for someone than they realize.
|
98 |
```
|
99 |
|
100 |
+
Another example of what you can use to chat multiple turns.
|
101 |
+
|
102 |
+
```python
|
103 |
+
messages = [
|
104 |
+
# {"role": "system", "content": "You are a helpful and knowledgeable assistant. You like to help and always give honest information, in its original language. In communication, you are always respectful, equal and promote positive behavior."},
|
105 |
+
{"role": "system", "content": "You are a helpful assistant."}, # Describe to your assistant, anything.
|
106 |
+
{"role": "user", "content": "Bla bla bla"},
|
107 |
+
{"role": "assistant", "content": "Bla bla bla"},
|
108 |
+
{"role": "user", "content": "Bla bla bla"},
|
109 |
+
]
|
110 |
+
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
111 |
+
tokenized = pipe.tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
|
112 |
+
outputs = pipe.model.generate(**tokenized, max_new_tokens=512)
|
113 |
+
results = tokenizer.batch_decode(outputs)[0]
|
114 |
+
print(results)
|
115 |
+
```
|
116 |
+
|
117 |
## More Information
|
118 |
|
119 |
Many thanks for
|