File size: 7,385 Bytes
e83fbb5
c28090d
da02d99
c28090d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7b77f4
 
c28090d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7b77f4
 
c28090d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7b77f4
 
c28090d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
### Run Huggingface RWKV6 World Model

> origin pth weight from https://huggingface.co/BlinkDL/rwkv-6-world/blob/main/RWKV-x060-World-1B6-v2.1-20240328-ctx4096.pth .

#### CPU

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

def generate_prompt(instruction, input=""):
    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
    input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
    if input:
        return f"""Instruction: {instruction}

Input: {input}

Response:"""
    else:
        return f"""User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: {instruction}

Assistant:"""


model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-6-world-1b6", trust_remote_code=True).to(torch.float32)
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-6-world-1b6", trust_remote_code=True, padding_side='left', pad_token="<s>")

text = "请介绍北京的旅游景点"
prompt = generate_prompt(text)

inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(inputs["input_ids"], max_new_tokens=333, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
```

output:

```shell
User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: 请介绍北京的旅游景点

Assistant: 北京是中国的首都,拥有众多的旅游景点,以下是其中一些著名的景点:
1. 故宫:位于北京市中心,是明清两代的皇宫,内有大量的文物和艺术品。
2. 天安门广场:是中国最著名的广场之一,是中国人民政治协商会议的旧址,也是中国人民政治协商会议的中心。
3. 颐和园:是中国古代皇家园林之一,有着悠久的历史和丰富的文化内涵。
4. 长城:是中国古代的一道长城,全长约万里,是中国最著名的旅游景点之一。
5. 北京大学:是中国著名的高等教育机构之一,有着悠久的历史和丰富的文化内涵。
6. 北京动物园:是中国最大的动物园之一,有着丰富的动物资源和丰富的文化内涵。
7. 故宫博物院:是中国最著名的博物馆之一,收藏了大量的文物和艺术品,是中国最重要的文化遗产之一。
8. 天坛:是中国古代皇家
```

#### GPU

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

def generate_prompt(instruction, input=""):
    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
    input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
    if input:
        return f"""Instruction: {instruction}

Input: {input}

Response:"""
    else:
        return f"""User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: {instruction}

Assistant:"""


model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-6-world-1b6", trust_remote_code=True, torch_dtype=torch.float16).to(0)
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-6-world-1b6", trust_remote_code=True, padding_side='left', pad_token="<s>")

text = "介绍一下大熊猫"
prompt = generate_prompt(text)

inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=128, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
```

output:

```shell
User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: 介绍一下大熊猫

Assistant: 大熊猫是一种中国特有的哺乳动物,也是中国的国宝之一。它们的外貌特征是圆形的黑白相间的身体,有着黑色的毛发和白色的耳朵。大熊猫的食物主要是竹子,它们会在竹林中寻找竹子,并且会将竹子放在竹笼中进行储存。大熊猫的寿命约为20至30年,但由于栖息地的丧失和人类活动的
```

#### Batch Inference

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

def generate_prompt(instruction, input=""):
    instruction = instruction.strip().replace('\r\n', '\n').replace('\n\n', '\n')
    input = input.strip().replace('\r\n', '\n').replace('\n\n', '\n')
    if input:
        return f"""Instruction: {instruction}

Input: {input}

Response:"""
    else:
        return f"""User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: {instruction}

Assistant:"""

model = AutoModelForCausalLM.from_pretrained("RWKV/rwkv-6-world-1b6", trust_remote_code=True).to(torch.float32)
tokenizer = AutoTokenizer.from_pretrained("RWKV/rwkv-6-world-1b6", trust_remote_code=True, padding_side='left', pad_token="<s>")

texts = ["请介绍北京的旅游景点", "介绍一下大熊猫", "乌兰察布"]
prompts = [generate_prompt(text) for text in texts]

inputs = tokenizer(prompts, return_tensors="pt", padding=True)
outputs = model.generate(inputs["input_ids"], max_new_tokens=128, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )

for output in outputs:
    print(tokenizer.decode(output.tolist(), skip_special_tokens=True))

```

output:

```shell
User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: 请介绍北京的旅游景点

Assistant: 北京是中国的首都,拥有丰富的旅游资源和历史文化遗产。以下是一些北京的旅游景点:
1. 故宫:位于北京市中心,是明清两代的皇宫,是中国最大的古代宫殿建筑群之一。
2. 天安门广场:位于北京市中心,是中国最著名的城市广场之一,也是中国最大的城市广场。
3. 颐和
User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: 介绍一下大熊猫

Assistant: 大熊猫是一种生活在中国中部地区的哺乳动物,也是中国的国宝之一。它们的外貌特征是圆形的黑白相间的身体,有着黑色的毛发和圆圆的眼睛。大熊猫是一种濒危物种,目前只有在野外的几个保护区才能看到它们的身影。大熊猫的食物主要是竹子,它们会在竹子上寻找食物,并且可以通
User: hi

Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.

User: 乌兰察布

Assistant: 乌兰察布是中国新疆维吾尔自治区的一个县级市,位于新疆维吾尔自治区中部,是新疆的第二大城市。乌兰察布市是新疆的第一大城市,也是新疆的重要城市之一。乌兰察布市是新疆的经济中心,也是新疆的重要交通枢纽之一。乌兰察布市的人口约为2.5万人,其中汉族占绝大多数。乌
```