File size: 6,529 Bytes
0046286
 
13070b9
 
 
 
 
 
0046286
2141a3c
a9fec40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
929e14b
a9fec40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2141a3c
a9fec40
 
 
 
 
 
 
 
28745a1
a9fec40
 
 
 
 
 
 
 
28745a1
a9fec40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28745a1
a9fec40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28745a1
a9fec40
 
 
 
 
 
 
 
28745a1
a9fec40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28745a1
a9fec40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13070b9
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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
---
library_name: keras-hub
license: apache-2.0
language:
- en
tags:
- text-generation
- text-conversation
---
## Model Overview
Mistral is a set of large language models published by the Mistral AI team. Both pretrained and instruction tuned models are available with 7 billion parameters. See the model card below for benchmarks, data sources, and intended use cases.

Both weights and Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).

## Links

* [Mistral 2 Quickstart Notebook](https://www.kaggle.com/code/matthewdwatson/mistral-quickstart)
* [Mistral 2 API Documentation](https://keras.io/api/keras_hub/models/mistral/)
* [Mistral 2 Model Card](https://huggingface.co/mistralai/Mistral-7B-v0.1)
* [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 instructions 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   |
|-----------------------|------------|---------------|
|` mistral_7b_en`          | 7.24B      | 7B base model |
| `mistral_instruct_7b_en ` | 	7.24B      | 7B instruction-tuned model |
| `mistral_0.2_instruct_7b_en ` | 	7.24B      | 7B instruction-tuned model version 0.2 |

## Prompts

Mistral "instruct" 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. See the following for an example:

```python
prompt = """[INST] Hello! [/INST] Hello! How are you? [INST] I'm great. Could you help me with a task? [/INST]
"""
```

Base models (without instruct in the name) have no specific prompting structure, and should usually be fine-tuned for a specific task.

## Example Usage
```python
import keras
import keras_hub
import numpy as np
```

Use `generate()` to do text generation.
```python
mistral_lm = keras_hub.models.MistralCausalLM.from_preset("mistral_instruct_7b_en")
mistral_lm.generate("[INST] What is Keras? [/INST]", max_length=500)

# Generate with batched prompts.
mistral_lm.generate(["[INST] What is Keras? [/INST]", "[INST] Give me your best brownie recipe. [/INST]"], max_length=500)
```

Compile the `generate()` function with a custom sampler.
```python
mistral_lm = keras_hub.models.MistralCausalLM.from_preset("mistral_instruct_7b_en")
mistral_lm.compile(sampler="greedy")
mistral_lm.generate("I want to say", max_length=30)

mistral_lm.compile(sampler=keras_hub.samplers.BeamSampler(num_beams=2))
mistral_lm.generate("I want to say", max_length=30)
```

Use `generate()` without preprocessing.
```python
prompt = {
    # `1` maps to the start token followed by "I want to say".
    "token_ids": np.array([[1, 315, 947, 298, 1315, 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, 1, 0, 0, 0, 0, 0]] * 2),
}

mistral_lm = keras_hub.models.MistralCausalLM.from_preset(
    "mistral_instruct_7b_en",
    preprocessor=None,
    dtype="bfloat16"
)
mistral_lm.generate(prompt)
```

Call `fit()` on a single batch.
```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
mistral_lm = keras_hub.models.MistralCausalLM.from_preset("mistral_instruct_7b_en")
mistral_lm.fit(x=features, batch_size=2)
```

Call `fit()` without preprocessing.
```python
x = {
    "token_ids": np.array([[1, 315, 947, 298, 1315, 369, 315, 837, 0, 0]] * 2),
    "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
y = np.array([[315, 947, 298, 1315, 369, 315, 837, 0, 0, 0]] * 2)
sw = np.array([[1, 1, 1, 1, 1, 1, 1, 0, 0, 0]] * 2)

mistral_lm = keras_hub.models.MistralCausalLM.from_preset(
    "mistral_instruct_7b_en",
    preprocessor=None,
    dtype="bfloat16"
)
mistral_lm.fit(x=x, y=y, sample_weight=sw, batch_size=2)
```

## Example Usage with Hugging Face URI

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

Use `generate()` to do text generation.
```python
mistral_lm = keras_hub.models.MistralCausalLM.from_preset("hf://keras/mistral_instruct_7b_en")
mistral_lm.generate("[INST] What is Keras? [/INST]", max_length=500)

# Generate with batched prompts.
mistral_lm.generate(["[INST] What is Keras? [/INST]", "[INST] Give me your best brownie recipe. [/INST]"], max_length=500)
```

Compile the `generate()` function with a custom sampler.
```python
mistral_lm = keras_hub.models.MistralCausalLM.from_preset("hf://keras/mistral_instruct_7b_en")
mistral_lm.compile(sampler="greedy")
mistral_lm.generate("I want to say", max_length=30)

mistral_lm.compile(sampler=keras_hub.samplers.BeamSampler(num_beams=2))
mistral_lm.generate("I want to say", max_length=30)
```

Use `generate()` without preprocessing.
```python
prompt = {
    # `1` maps to the start token followed by "I want to say".
    "token_ids": np.array([[1, 315, 947, 298, 1315, 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, 1, 0, 0, 0, 0, 0]] * 2),
}

mistral_lm = keras_hub.models.MistralCausalLM.from_preset(
    "hf://keras/mistral_instruct_7b_en",
    preprocessor=None,
    dtype="bfloat16"
)
mistral_lm.generate(prompt)
```

Call `fit()` on a single batch.
```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
mistral_lm = keras_hub.models.MistralCausalLM.from_preset("hf://keras/mistral_instruct_7b_en")
mistral_lm.fit(x=features, batch_size=2)
```

Call `fit()` without preprocessing.
```python
x = {
    "token_ids": np.array([[1, 315, 947, 298, 1315, 369, 315, 837, 0, 0]] * 2),
    "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
y = np.array([[315, 947, 298, 1315, 369, 315, 837, 0, 0, 0]] * 2)
sw = np.array([[1, 1, 1, 1, 1, 1, 1, 0, 0, 0]] * 2)

mistral_lm = keras_hub.models.MistralCausalLM.from_preset(
    "hf://keras/mistral_instruct_7b_en",
    preprocessor=None,
    dtype="bfloat16"
)
mistral_lm.fit(x=x, y=y, sample_weight=sw, batch_size=2)
```