File size: 5,710 Bytes
a4b50d3
 
 
1af83a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
library_name: keras-hub
---
### Model Overview
Phi-3 is a set of large language models published by Microsoft. Models are instruction tuned, and range in size from 3 billion to 14 billion parameters. See the model card below for benchmarks, data sources, and intended use cases.

Weights are released under the [MIT License](https://opensource.org/license/mit). Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).

## Links

* [Phi-3 Quickstart Notebook](https://www.kaggle.com/code/matthewdwatson/phi-3-quickstart)
* [Phi-3 API Documentation](https://keras.io/api/keras_hub/models/phi3/)
* [Phi-3 Model Card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
* [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/)

## Installation

Keras and KerasHub can be installed with:

```
pip install -U -q keras-hub
pip install -U -q keras>=3
```

Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instruction on installing them in another environment see the [Keras Getting Started](https://keras.io/getting_started/) page.

## Presets

The following model checkpoints are provided by the Keras team. Full code examples for each are available below.

| Preset name           | Parameters | Description   |
|-----------------------|------------|---------------|
|` phi3_mini_4k_instruct_en`          | 3.82B      | 3B model with 4K max context |
| `phi3_mini_128k_instruct_en` | 3.82B      | 3B model with 128K max context |

## Prompts

Phi-3 models are instruction tuned on turn by turn conversations and should be prompted with examples that precisely match the training data. Specifically, you must alternate user and assistant turns that begin and end with special tokens. New lines do matter. See the following for an example:

```python
prompt = """<|user|>
Hello!<|end|>
<|assistant|>
Hello! How are you?<|end|>
<|user|>
I'm great. Could you help me with a task?<|end|>
"""
```

## Example Usage
```shell
pip install -U -q keras-hub
```

```python
import keras
import keras_hub
import numpy as np
```

Use `generate()` to do text generation.

```python
phi3_lm = keras_hub.models.Phi3CausalLM.from_preset("phi3_mini_4k_instruct_en")
phi3_lm.generate("<|user|>\nHow to explain Internet for a medieval knight?<|end|>\n<|assistant|>", max_length=500)

# Generate with batched prompts.
phi3_lm.generate([
    "<|user|>\nWhat is Keras?<|end|>\n<|assistant|>",
    "<|user|>\nGive me your best brownie recipe.<|end|>\n<|assistant|>",
], max_length=500)
```

Compile the `generate()` function with a custom sampler.

```python
phi3_lm = keras_hub.models.Phi3CausalLM.from_preset("phi3_mini_4k_instruct_en")
phi3_lm.compile(sampler="greedy")
phi3_lm.generate("<|user|>\nWhat is Keras?<|end|>\n<|assistant|>", max_length=30)

phi3_lm.compile(sampler=keras_hub.samplers.BeamSampler(num_beams=2))
phi3_lm.generate("<|user|>\nWhat is Keras?<|end|>\n<|assistant|>", max_length=30)
```

Use `generate()` without preprocessing.

```python
prompt = {
    "token_ids": np.array([[306, 864, 304, 1827, 0, 0, 0, 0, 0, 0]] * 2),
    # Use `"padding_mask"` to indicate values that should not be overridden.
    "padding_mask": np.array([[1, 1, 1, 1, 0, 0, 0, 0, 0, 0]] * 2),
}

phi3_lm = keras_hub.models.Phi3CausalLM.from_preset(
    "phi3_mini_4k_instruct_en",
    preprocessor=None,
    dtype="bfloat16"
)
phi3_lm.generate(prompt)
```

Call `fit()` on a single batch.

```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
phi3_lm = keras_hub.models.Phi3CausalLM.from_preset("phi3_mini_4k_instruct_en")
phi3_lm.fit(x=features, batch_size=2)
```

## Example Usage with Hugging Face URI

```shell
pip install -U -q keras-hub
```

```python
import keras
import keras_hub
import numpy as np
```

Use `generate()` to do text generation.

```python
phi3_lm = keras_hub.models.Phi3CausalLM.from_preset("hf://keras/phi3_mini_4k_instruct_en")
phi3_lm.generate("<|user|>\nHow to explain Internet for a medieval knight?<|end|>\n<|assistant|>", max_length=500)

# Generate with batched prompts.
phi3_lm.generate([
    "<|user|>\nWhat is Keras?<|end|>\n<|assistant|>",
    "<|user|>\nGive me your best brownie recipe.<|end|>\n<|assistant|>",
], max_length=500)
```

Compile the `generate()` function with a custom sampler.

```python
phi3_lm = keras_hub.models.Phi3CausalLM.from_preset("hf://keras/phi3_mini_4k_instruct_en")
phi3_lm.compile(sampler="greedy")
phi3_lm.generate("<|user|>\nWhat is Keras?<|end|>\n<|assistant|>", max_length=30)

phi3_lm.compile(sampler=keras_hub.samplers.BeamSampler(num_beams=2))
phi3_lm.generate("<|user|>\nWhat is Keras?<|end|>\n<|assistant|>", max_length=30)
```

Use `generate()` without preprocessing.

```python
prompt = {
    "token_ids": np.array([[306, 864, 304, 1827, 0, 0, 0, 0, 0, 0]] * 2),
    # Use `"padding_mask"` to indicate values that should not be overridden.
    "padding_mask": np.array([[1, 1, 1, 1, 0, 0, 0, 0, 0, 0]] * 2),
}

phi3_lm = keras_hub.models.Phi3CausalLM.from_preset(
    "hf://keras/phi3_mini_4k_instruct_en",
    preprocessor=None,
    dtype="bfloat16"
)
phi3_lm.generate(prompt)
```

Call `fit()` on a single batch.

```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
phi3_lm = keras_hub.models.Phi3CausalLM.from_preset("hf://keras/phi3_mini_4k_instruct_en")
phi3_lm.fit(x=features, batch_size=2)
```