Update README.md
Browse files
README.md
CHANGED
@@ -28,14 +28,7 @@ license: other
|
|
28 |
|
29 |
## Usage
|
30 |
|
31 |
-
`StableLM 2
|
32 |
-
```
|
33 |
-
<|user|>
|
34 |
-
Which famous math number begins with 1.6 ...?<|endoftext|>
|
35 |
-
<|assistant|>
|
36 |
-
The number you are referring to is 1.618033988749895. This is the famous value known as the golden ratio<|endoftext|>
|
37 |
-
```
|
38 |
-
|
39 |
This format is also available through the tokenizer's `apply_chat_template` method:
|
40 |
|
41 |
```python
|
@@ -65,6 +58,69 @@ tokens = model.generate(
|
|
65 |
print(tokenizer.decode(tokens[0], skip_special_tokens=False))
|
66 |
```
|
67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
## Model Details
|
69 |
|
70 |
* **Developed by**: [Stability AI](https://stability.ai/)
|
|
|
28 |
|
29 |
## Usage
|
30 |
|
31 |
+
`StableLM 2 Chat` uses the following instruction ChatML format
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
This format is also available through the tokenizer's `apply_chat_template` method:
|
33 |
|
34 |
```python
|
|
|
58 |
print(tokenizer.decode(tokens[0], skip_special_tokens=False))
|
59 |
```
|
60 |
|
61 |
+
StableLM 2 Chat also supports function call usage this is an example how you can use it:
|
62 |
+
```python
|
63 |
+
system_prompt_func = """\
|
64 |
+
You are a helpful assistant with access to the following functions. You must use them if required -\n
|
65 |
+
[
|
66 |
+
{
|
67 |
+
"type": "function",
|
68 |
+
"function": {
|
69 |
+
"name": "TextToImage",
|
70 |
+
"description": "This function able to creating, drawing, or illustrating an image from a text prompt.",
|
71 |
+
"parameters": {
|
72 |
+
"type": "object",
|
73 |
+
"properties": {
|
74 |
+
"prompt": {
|
75 |
+
"type": "string",
|
76 |
+
"description": "The description of image that user wanto to create."
|
77 |
+
}
|
78 |
+
},
|
79 |
+
"required": [
|
80 |
+
"prompt"
|
81 |
+
]
|
82 |
+
}
|
83 |
+
}
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"type": "function",
|
87 |
+
"function": {
|
88 |
+
"name": "EditImage",
|
89 |
+
"description": "This is capable of changing, editing, adjusting, or modifying an image by describing changes to the image through a text prompt.",
|
90 |
+
"parameters": {
|
91 |
+
"type": "object",
|
92 |
+
"properties": {
|
93 |
+
"prompt": {
|
94 |
+
"type": "string",
|
95 |
+
"description": "The instruction used to edit the image."
|
96 |
+
}
|
97 |
+
},
|
98 |
+
"required": [
|
99 |
+
"prompt"
|
100 |
+
]
|
101 |
+
}
|
102 |
+
}
|
103 |
+
}
|
104 |
+
]
|
105 |
+
"""
|
106 |
+
messages = [{'role': 'system', 'content': system_prompt_func}, "user": "Help me to generate a picture of Eiffel Tower in the night!"]
|
107 |
+
inputs = tokenizer.apply_chat_template(
|
108 |
+
prompt,
|
109 |
+
add_generation_prompt=True,
|
110 |
+
return_tensors='pt'
|
111 |
+
)
|
112 |
+
|
113 |
+
tokens = model.generate(
|
114 |
+
inputs.to(model.device),
|
115 |
+
max_new_tokens=1024,
|
116 |
+
temperature=0.5,
|
117 |
+
do_sample=True
|
118 |
+
)
|
119 |
+
|
120 |
+
print(tokenizer.decode(tokens[0], skip_special_tokens=False))
|
121 |
+
```
|
122 |
+
|
123 |
+
|
124 |
## Model Details
|
125 |
|
126 |
* **Developed by**: [Stability AI](https://stability.ai/)
|