Transformers
llamafile
mixtral
File size: 20,726 Bytes
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
59f4894
29fb37a
 
 
59f4894
29fb37a
 
 
 
 
 
59f4894
29fb37a
59f4894
 
 
29fb37a
59f4894
29fb37a
59f4894
29fb37a
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
59f4894
 
 
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
59f4894
29fb37a
 
 
 
59f4894
 
 
 
 
 
 
 
29fb37a
 
 
 
 
59f4894
29fb37a
59f4894
 
29fb37a
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
59f4894
29fb37a
59f4894
29fb37a
 
 
 
 
59f4894
29fb37a
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59f4894
29fb37a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
---
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
inference: false
language:
- fr
- it
- de
- es
- en
license: apache-2.0
model_creator: Mistral AI_
model_name: Mixtral 8X7B Instruct v0.1
model_type: mixtral
prompt_template: '[INST] {prompt} [/INST]

  '
quantized_by: TheBloke
widget:
- output:
    text: 'Arr, shiver me timbers! Ye have a llama on yer lawn, ye say? Well, that
      be a new one for me! Here''s what I''d suggest, arr:


      1. Firstly, ensure yer safety. Llamas may look gentle, but they can be protective
      if they feel threatened.

      2. Try to make the area less appealing to the llama. Remove any food sources
      or water that might be attracting it.

      3. Contact local animal control or a wildlife rescue organization. They be the
      experts and can provide humane ways to remove the llama from yer property.

      4. If ye have any experience with animals, you could try to gently herd the
      llama towards a nearby field or open space. But be careful, arr!


      Remember, arr, it be important to treat the llama with respect and care. It
      be a creature just trying to survive, like the rest of us.'
  text: '[INST] You are a pirate chatbot who always responds with Arr and pirate speak!

    There''s a llama on my lawn, how can I get rid of him? [/INST]'
---
<!-- markdownlint-disable MD041 -->

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/FwAVVu7eJ4">Chat & support: jartine's Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
    </div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">jartine's LLM work is generously supported by a grant from <a href="https://mozilla.org">mozilla</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Mixtral 8X7B Instruct v0.1 - llamafile
- Model creator: [Mistral AI_](https://huggingface.co/mistralai)
- Original model: [Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)

<!-- description start -->
## Description

This repo contains llamafile format model files for [Mistral AI_'s Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1).

WARNING: This README may contain inaccuracies. It was generated automatically by forking <a href=/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF>TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF</a> and piping the README through sed. Errors should be reported to jartine, and do not reflect TheBloke. You can also support his work on [Patreon](https://www.patreon.com/TheBlokeAI).
<!-- README_llamafile.md-about-llamafile start -->
### About llamafile

llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp binaries that run on the stock installs of six OSes for both ARM64 and AMD64.

### Mixtral llamafile

Support for Mixtral was merged into Llama.cpp on December 13th.

These Mixtral llamafiles are known to work in:

* llama.cpp as of December 13th
* KoboldCpp 1.52 as later
* LM Studio 0.2.9 and later
* llama-cpp-python 0.2.23 and later

Other clients/libraries, not listed above, may not yet work.

<!-- README_llamafile.md-about-llamafile end -->
<!-- repositories-available start -->
## Repositories available

* [AWQ model(s) for GPU inference.](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit llamafile models for CPU+GPU inference](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile)
* [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
<!-- repositories-available end -->

<!-- prompt-template start -->
## Prompt template: Mistral

```
[INST] {prompt} [/INST]

```

<!-- prompt-template end -->


<!-- compatibility_llamafile start -->
## Compatibility

These Mixtral llamafiles are compatible with llama.cpp from December 13th onwards. Other clients/libraries may not work yet.

## Explanation of quantisation methods

<details>
  <summary>Click to see details</summary>

The new methods available are:

* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_llamafile end -->

<!-- README_llamafile.md-provided-files start -->
## Provided files

| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [mixtral-8x7b-instruct-v0.1.Q2_K.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q2_K.llamafile) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes |
| [mixtral-8x7b-instruct-v0.1.Q3_K_M.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q3_K_M.llamafile) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss |
| [mixtral-8x7b-instruct-v0.1.Q4_0.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q4_0.llamafile) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended |
| [mixtral-8x7b-instruct-v0.1.Q5_0.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q5_0.llamafile) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [mixtral-8x7b-instruct-v0.1.Q5_K_M.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q5_K_M.llamafile) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended |
| [mixtral-8x7b-instruct-v0.1.Q6_K.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q6_K.llamafile) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss |
| [mixtral-8x7b-instruct-v0.1.Q8_0.llamafile](https://huggingface.co/jartine/Mixtral-8x7B-Instruct-v0.1-llamafile/blob/main/mixtral-8x7b-instruct-v0.1.Q8_0.llamafile) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended |

**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.



<!-- README_llamafile.md-provided-files end -->

<!-- README_llamafile.md-how-to-download start -->
## How to download llamafile files

**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

* LM Studio
* LoLLMS Web UI
* Faraday.dev

### In `text-generation-webui`

Under Download Model, you can enter the model repo: jartine/Mixtral-8x7B-Instruct-v0.1-llamafile and below it, a specific filename to download, such as: mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile.

Then click Download.

### On the command line, including multiple files at once

I recommend using the `huggingface-hub` Python library:

```shell
pip3 install huggingface-hub
```

Then you can download any individual model file to the current directory, at high speed, with a command like this:

```shell
huggingface-cli download jartine/Mixtral-8x7B-Instruct-v0.1-llamafile mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile --local-dir . --local-dir-use-symlinks False
```

<details>
  <summary>More advanced huggingface-cli download usage (click to read)</summary>

You can also download multiple files at once with a pattern:

```shell
huggingface-cli download jartine/Mixtral-8x7B-Instruct-v0.1-llamafile --local-dir . --local-dir-use-symlinks False --include='*Q4_K*llamafile'
```

For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).

To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:

```shell
pip3 install hf_transfer
```

And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:

```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download jartine/Mixtral-8x7B-Instruct-v0.1-llamafile mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile --local-dir . --local-dir-use-symlinks False
```

Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_llamafile.md-how-to-download end -->

<!-- README_llamafile.md-how-to-run start -->
## Example `llama.cpp` command

Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.

```shell
./main -ngl 35 -m mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] {prompt} [/INST]"
```

Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the llamafile file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.

If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`

For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)

## How to run in `text-generation-webui`

Note that text-generation-webui may not yet be compatible with Mixtral llamafiles. Please check compatibility first.

Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).

## How to run from Python code

You can use llamafile models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) version 0.2.23 and later.

### How to load this model in Python code, using llama-cpp-python

For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).

#### First install the package

Run one of the following commands, according to your system:

```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```

#### Simple llama-cpp-python example code

```python
from llama_cpp import Llama

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
  model_path="./mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile",  # Download the model file first
  n_ctx=2048,  # The max sequence length to use - note that longer sequence lengths require much more resources
  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
)

# Simple inference example
output = llm(
  "[INST] {prompt} [/INST]", # Prompt
  max_tokens=512,  # Generate up to 512 tokens
  stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
  echo=True        # Whether to echo the prompt
)

# Chat Completion API

llm = Llama(model_path="./mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile", chat_format="llama-2")  # Set chat_format according to the model you are using
llm.create_chat_completion(
    messages = [
        {"role": "system", "content": "You are a story writing assistant."},
        {
            "role": "user",
            "content": "Write a story about llamas."
        }
    ]
)
```

## How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)

<!-- README_llamafile.md-how-to-run end -->

<!-- footer start -->
<!-- 200823 -->
## Discord

For further support, and discussions on these models and AI in general, join us at:

[jartine AI's Discord server](https://discord.gg/FwAVVu7eJ4)

## Thanks, and how to contribute



I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.







And thank you again to mozilla for their generous grant.

<!-- footer end -->

<!-- original-model-card start -->
# Original model card: Mistral AI_'s Mixtral 8X7B Instruct v0.1

# Model Card for Mixtral-8x7B
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.

For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/).

## Warning
This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF.

## Instruction format

This format must be strictly respected, otherwise the model will generate sub-optimal outputs.

The template used to build a prompt for the Instruct model is defined as follows:
```
<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
```
Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.

As reference, here is the pseudo-code used to tokenize instructions during fine-tuning:
```python
def tokenize(text):
    return tok.encode(text, add_special_tokens=False)

[BOS_ID] +
tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_1) + [EOS_ID] +

tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") +
tokenize(BOT_MESSAGE_N) + [EOS_ID]
```

In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space.

## Run the model

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)

text = "Hello my name is"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem:

### In half-precision

Note `float16` precision only works on GPU devices

<details>
<summary> Click to expand </summary>

```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0)

text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>

### Lower precision using (8-bit & 4-bit) using `bitsandbytes`

<details>
<summary> Click to expand </summary>

```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True)

text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>

### Load the model with Flash Attention 2

<details>
<summary> Click to expand </summary>

```diff
+ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)

+ model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True)

text = "Hello my name is"
+ inputs = tokenizer(text, return_tensors="pt").to(0)

outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
</details>

## Limitations

The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.

# The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

<!-- original-model-card end -->