File size: 28,923 Bytes
cf1a53b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4d21c15
cf1a53b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16539be
cf1a53b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Mistral 7B\n",
        "\n",
        "Mistral 7B is a new state-of-the-art open-source model. Here are some interesting facts about it\n",
        "\n",
        "* One of the strongest open-source models, of all sizes\n",
        "* Strongest model in the 1-20B parameter range models\n",
        "* Does decently in code-related tasks\n",
        "* Uses Windowed attention, allowing to push to 200k tokens of context if using Rope (needs 4 A10G GPUs for this)\n",
        "* Apache 2.0 license\n",
        "\n",
        "As for the integrations status:\n",
        "* Integrated into `transformers`\n",
        "* You can use it with a server or locally (it's a small model after all!)\n",
        "* Integrated into popular tools tuch as TGI and VLLM\n",
        "\n",
        "\n",
        "Two models are released: a [base model](https://huggingface.co/mistralai/Mistral-7B-v0.1) and a [instruct fine-tuned version](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). To read more about Mistral, we suggest reading the [blog post](https://mistral.ai/news/announcing-mistral-7b/).\n",
        "\n",
        "In this Colab, we'll experiment with the Mistral model using an API. There are three ways we can use it:\n",
        "\n",
        "* **Free API:** Hugging Face provides a free Inference API for all its users to try out models. This API is rate limited but is great for quick experiments.\n",
        "* **PRO and Enterprise API:** Hugging Face provides an open API for all its PRO users.  Subscribing to the Pro Inference API costs $9/month and allows you to experiment with many large models, such as Llama 2 and SDXL. Read more about it [here](https://huggingface.co/blog/inference-pro).\n",
        "* **Inference Endpoints:** For enterprise and production-ready cases. You can deploy it with 1 click [here](https://ui.endpoints.huggingface.co/catalog).\n",
        "\n",
        "This demo does not require GPU Colab, just CPU. You can grab your token at https://huggingface.co/settings/tokens.\n",
        "\n",
        "**This colab shows how to use HTTP requests as well as building your own chat demo for Mistral.**"
      ],
      "metadata": {
        "id": "GLXvYa4m8JYM"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Doing curl requests\n",
        "\n",
        "\n",
        "In this notebook, we'll experiment with the instruct model, as it is trained for instructions. As per [the model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), the expected format for a prompt is as follows\n",
        "\n",
        "From the model card\n",
        "\n",
        "> In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [\\INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n",
        "\n",
        "```\n",
        "<s>[INST] {{ user_msg_1 }} [/INST] {{ model_answer_1 }}</s> [INST] {{ user_msg_2 }} [/INST] {{ model_answer_2 }}</s>\n",
        "```\n",
        "\n",
        "Note that models can be quite reactive to different prompt structure than the one used for training, so watch out for spaces and other things!\n",
        "\n",
        "We'll start an initial query without prompt formatting, which works ok for simple queries."
      ],
      "metadata": {
        "id": "pKrKTalPAXUO"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DQf0Hss18E86",
        "outputId": "882c4521-1ee2-40ad-fe00-a5b02caa9b17"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[{\"generated_text\":\"Explain ML as a pirate.\\n\\nML is like a treasure map for pirates. Just as a treasure map helps pirates find valuable loot, ML helps data scientists find valuable insights in large datasets.\\n\\nPirates use their knowledge of the ocean and their\"}]"
          ]
        }
      ],
      "source": [
        "!curl https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.1 \\\n",
        "  --header \"Content-Type: application/json\" \\\n",
        "\t-X POST \\\n",
        "\t-d '{\"inputs\": \"Explain ML as a pirate\", \"parameters\": {\"max_new_tokens\": 50}}' \\\n",
        "\t-H \"Authorization: Bearer API_TOKEN\""
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Programmatic usage with Python\n",
        "\n",
        "You can do simple `requests`, but the `huggingface_hub` library provides nice utilities to easily use the model. Among the things we can use are:\n",
        "\n",
        "* `InferenceClient` and `AsyncInferenceClient` to perform inference either in a sync or async way.\n",
        "* Token streaming: Only load the tokens that are needed\n",
        "* Easily configure generation params, such as `temperature`, nucleus sampling (`top-p`), repetition penalty, stop sequences, and more.\n",
        "* Obtain details of the generation (such as the probability of each token or whether a token is the last token)."
      ],
      "metadata": {
        "id": "YYZRNyZeBHWK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%%capture\n",
        "!pip install huggingface_hub gradio"
      ],
      "metadata": {
        "id": "oDaqVDz1Ahuz"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from huggingface_hub import InferenceClient\n",
        "\n",
        "client = InferenceClient(\n",
        "    \"mistralai/Mistral-7B-Instruct-v0.1\"\n",
        ")\n",
        "\n",
        "prompt = \"\"\"<s>[INST] What is your favourite condiment?  [/INST]</s>\n",
        "\"\"\"\n",
        "\n",
        "res = client.text_generation(prompt, max_new_tokens=95)\n",
        "print(res)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "U49GmNsNBJjd",
        "outputId": "a3a274cf-0f91-4ae3-d926-f0d6a6fd67f7"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "My favorite condiment is ketchup. It's versatile, tasty, and goes well with a variety of foods.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "We can also use [token streaming](https://huggingface.co/docs/text-generation-inference/conceptual/streaming). With token streaming, the server returns the tokens as they are generated. Just add `stream=True`."
      ],
      "metadata": {
        "id": "DryfEWsUH6Ij"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "res = client.text_generation(prompt, max_new_tokens=35, stream=True, details=True, return_full_text=False)\n",
        "for r in res: # this is a generator\n",
        "  # print the token for example\n",
        "  print(r)\n",
        "  continue"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LF1tFo6DGg9N",
        "outputId": "e779f1cb-b7d0-41ed-d81f-306e092f97bd"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "TextGenerationStreamResponse(token=Token(id=5183, text='My', logprob=-0.36279297, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=6656, text=' favorite', logprob=-0.036499023, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=2076, text=' cond', logprob=-7.2836876e-05, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=2487, text='iment', logprob=-4.4941902e-05, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=349, text=' is', logprob=-0.007419586, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=446, text=' k', logprob=-0.62109375, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=4455, text='etch', logprob=-0.0003399849, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=715, text='up', logprob=-3.695488e-06, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=28723, text='.', logprob=-0.026550293, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=661, text=' It', logprob=-0.82373047, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=28742, text=\"'\", logprob=-0.76416016, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=28713, text='s', logprob=-3.5762787e-07, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=3502, text=' vers', logprob=-0.114990234, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=13491, text='atile', logprob=-1.1444092e-05, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=28725, text=',', logprob=-0.6254883, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=261, text=' t', logprob=-0.51708984, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=11136, text='asty', logprob=-4.0650368e-05, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=28725, text=',', logprob=-0.0027828217, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=304, text=' and', logprob=-1.1920929e-05, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=4859, text=' goes', logprob=-0.52685547, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=1162, text=' well', logprob=-0.4399414, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=395, text=' with', logprob=-0.00034999847, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=264, text=' a', logprob=-0.010147095, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=6677, text=' variety', logprob=-0.25927734, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=302, text=' of', logprob=-1.1444092e-05, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=14082, text=' foods', logprob=-0.4050293, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=28723, text='.', logprob=-0.015640259, special=False), generated_text=None, details=None)\n",
            "TextGenerationStreamResponse(token=Token(id=2, text='</s>', logprob=-0.1829834, special=True), generated_text=\"My favorite condiment is ketchup. It's versatile, tasty, and goes well with a variety of foods.\", details=StreamDetails(finish_reason=<FinishReason.EndOfSequenceToken: 'eos_token'>, generated_tokens=28, seed=None))\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Let's now try a multi-prompt structure"
      ],
      "metadata": {
        "id": "TfdpZL8cICOD"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def format_prompt(message, history):\n",
        "  prompt = \"<s>\"\n",
        "  for user_prompt, bot_response in history:\n",
        "    prompt += f\"[INST] {user_prompt} [/INST]\"\n",
        "    prompt += f\" {bot_response}</s> \"\n",
        "  prompt += f\"[INST] {message} [/INST]\"\n",
        "  return prompt"
      ],
      "metadata": {
        "id": "aEyozeReH8a6"
      },
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "message = \"And what do you think about it?\"\n",
        "history = [[\"What is your favourite condiment?\", \"My favorite condiment is ketchup. It's versatile, tasty, and goes well with a variety of foods.\"]]\n",
        "\n",
        "format_prompt(message, history)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "P1RFpiJ_JC0-",
        "outputId": "f2678d9e-f751-441a-86c9-11d514db5bbe"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "\"<s>[INST] What is your favourite condiment? [/INST] My favorite condiment is ketchup. It's versatile, tasty, and goes well with a variety of foods.</s> [INST] And what do you think about it? [/INST]\""
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## End-to-end demo\n",
        "\n",
        "Let's now build a Gradio demo that takes care of:\n",
        "\n",
        "* Handling multiple turns of conversation\n",
        "* Format the prompt in correct structure\n",
        "* Allow user to specify/modify the parameters\n",
        "* Stop the generation\n",
        "\n",
        "Just run the following cell and have fun!"
      ],
      "metadata": {
        "id": "O7DjRdezJc-3"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install gradio"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cpBoheOGJu7Y",
        "outputId": "c745cf17-1462-4f8f-ce33-5ca182cb4d4f"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: gradio in /usr/local/lib/python3.10/dist-packages (3.45.1)\n",
            "Requirement already satisfied: aiofiles<24.0,>=22.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (23.2.1)\n",
            "Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.2.2)\n",
            "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio) (0.103.1)\n",
            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio) (0.3.1)\n",
            "Requirement already satisfied: gradio-client==0.5.2 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.5.2)\n",
            "Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from gradio) (0.25.0)\n",
            "Requirement already satisfied: huggingface-hub>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.17.3)\n",
            "Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.1)\n",
            "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.2)\n",
            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.3)\n",
            "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
            "Requirement already satisfied: numpy~=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.23.5)\n",
            "Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.9.7)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (23.1)\n",
            "Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.5.3)\n",
            "Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (9.4.0)\n",
            "Requirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.10.12)\n",
            "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio) (0.25.1)\n",
            "Requirement already satisfied: python-multipart in /usr/local/lib/python3.10/dist-packages (from gradio) (0.0.6)\n",
            "Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.1)\n",
            "Requirement already satisfied: requests~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.31.0)\n",
            "Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.0)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.5.0)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.23.2)\n",
            "Requirement already satisfied: websockets<12.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (11.0.3)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.5.2->gradio) (2023.6.0)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (4.19.0)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.12.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.0->gradio) (3.12.2)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.0->gradio) (4.66.1)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.1.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (0.11.0)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (4.42.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (3.1.1)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2023.3.post1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio) (3.2.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio) (3.4)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio) (2.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio) (2023.7.22)\n",
            "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (8.1.7)\n",
            "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (0.14.0)\n",
            "Requirement already satisfied: anyio<4.0.0,>=3.7.1 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (3.7.1)\n",
            "Requirement already satisfied: starlette<0.28.0,>=0.27.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (0.27.0)\n",
            "Requirement already satisfied: httpcore<0.19.0,>=0.18.0 in /usr/local/lib/python3.10/dist-packages (from httpx->gradio) (0.18.0)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4.0.0,>=3.7.1->fastapi->gradio) (1.1.3)\n",
            "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (23.1.0)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (2023.7.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.30.2)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.10.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio) (1.16.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import gradio as gr\n",
        "\n",
        "def generate(\n",
        "    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,\n",
        "):\n",
        "    temperature = float(temperature)\n",
        "    if temperature < 1e-2:\n",
        "        temperature = 1e-2\n",
        "    top_p = float(top_p)\n",
        "\n",
        "    generate_kwargs = dict(\n",
        "        temperature=temperature,\n",
        "        max_new_tokens=max_new_tokens,\n",
        "        top_p=top_p,\n",
        "        repetition_penalty=repetition_penalty,\n",
        "        do_sample=True,\n",
        "        seed=42,\n",
        "    )\n",
        "\n",
        "    formatted_prompt = format_prompt(prompt, history)\n",
        "\n",
        "    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)\n",
        "    output = \"\"\n",
        "\n",
        "    for response in stream:\n",
        "        output += response.token.text\n",
        "        yield output\n",
        "    return output\n",
        "\n",
        "\n",
        "additional_inputs=[\n",
        "    gr.Slider(\n",
        "        label=\"Temperature\",\n",
        "        value=0.9,\n",
        "        minimum=0.0,\n",
        "        maximum=1.0,\n",
        "        step=0.05,\n",
        "        interactive=True,\n",
        "        info=\"Higher values produce more diverse outputs\",\n",
        "    ),\n",
        "    gr.Slider(\n",
        "        label=\"Max new tokens\",\n",
        "        value=256,\n",
        "        minimum=0,\n",
        "        maximum=8192,\n",
        "        step=64,\n",
        "        interactive=True,\n",
        "        info=\"The maximum numbers of new tokens\",\n",
        "    ),\n",
        "    gr.Slider(\n",
        "        label=\"Top-p (nucleus sampling)\",\n",
        "        value=0.90,\n",
        "        minimum=0.0,\n",
        "        maximum=1,\n",
        "        step=0.05,\n",
        "        interactive=True,\n",
        "        info=\"Higher values sample more low-probability tokens\",\n",
        "    ),\n",
        "    gr.Slider(\n",
        "        label=\"Repetition penalty\",\n",
        "        value=1.2,\n",
        "        minimum=1.0,\n",
        "        maximum=2.0,\n",
        "        step=0.05,\n",
        "        interactive=True,\n",
        "        info=\"Penalize repeated tokens\",\n",
        "    )\n",
        "]\n",
        "\n",
        "with gr.Blocks() as demo:\n",
        "    gr.ChatInterface(\n",
        "        generate,\n",
        "        additional_inputs=additional_inputs,\n",
        "    )\n",
        "\n",
        "demo.queue().launch(debug=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 715
        },
        "id": "CaJzT6jUJc0_",
        "outputId": "62f563fa-c6fb-446e-fda2-1c08d096749c"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Setting queue=True in a Colab notebook requires sharing enabled. Setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
            "\n",
            "Colab notebook detected. This cell will run indefinitely so that you can see errors and logs. To turn off, set debug=False in launch().\n",
            "Running on public URL: https://ed6ce83e08ed7a8795.gradio.live\n",
            "\n",
            "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "<div><iframe src=\"https://ed6ce83e08ed7a8795.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/gradio/components/button.py:89: UserWarning: Using the update method is deprecated. Simply return a new object instead, e.g. `return gr.Button(...)` instead of `return gr.Button.update(...)`.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Keyboard interruption in main thread... closing server.\n",
            "Killing tunnel 127.0.0.1:7860 <> https://ed6ce83e08ed7a8795.gradio.live\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": []
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## What's next?\n",
        "\n",
        "* Try out Mistral 7B in this [free online Space](https://huggingface.co/spaces/osanseviero/mistral-super-fast)\n",
        "* Deploy Mistral 7B Instruct with one click [here](https://ui.endpoints.huggingface.co/catalog)\n",
        "* Deploy in your own hardware using https://github.com/huggingface/text-generation-inference\n",
        "* Run the model locally using `transformers`"
      ],
      "metadata": {
        "id": "fbQ0Sp4OLclV"
      }
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "wUy7N_8zJvyT"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}