TheBloke commited on
Commit
8ba6f48
·
verified ·
1 Parent(s): e7b8797

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +499 -0
README.md ADDED
@@ -0,0 +1,499 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Unbabel/TowerInstruct-7B-v0.1
3
+ inference: false
4
+ language:
5
+ - en
6
+ - de
7
+ - fr
8
+ - zh
9
+ - pt
10
+ - nl
11
+ - ru
12
+ - ko
13
+ - it
14
+ - es
15
+ license: cc-by-nc-4.0
16
+ metrics:
17
+ - comet
18
+ model_creator: Unbabel
19
+ model_name: TowerInstruct 7B v0.1
20
+ model_type: llama
21
+ pipeline_tag: translation
22
+ prompt_template: '<|im_start|>system
23
+
24
+ {system_message}<|im_end|>
25
+
26
+ <|im_start|>user
27
+
28
+ {prompt}<|im_end|>
29
+
30
+ <|im_start|>assistant
31
+
32
+ '
33
+ quantized_by: TheBloke
34
+ ---
35
+ <!-- markdownlint-disable MD041 -->
36
+
37
+ <!-- header start -->
38
+ <!-- 200823 -->
39
+ <div style="width: auto; margin-left: auto; margin-right: auto">
40
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
41
+ </div>
42
+ <div style="display: flex; justify-content: space-between; width: 100%;">
43
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
44
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
45
+ </div>
46
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
47
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
48
+ </div>
49
+ </div>
50
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
51
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
52
+ <!-- header end -->
53
+
54
+ # TowerInstruct 7B v0.1 - AWQ
55
+ - Model creator: [Unbabel](https://huggingface.co/Unbabel)
56
+ - Original model: [TowerInstruct 7B v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1)
57
+
58
+ <!-- description start -->
59
+ ## Description
60
+
61
+ This repo contains AWQ model files for [Unbabel's TowerInstruct 7B v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1).
62
+
63
+
64
+ ### About AWQ
65
+
66
+ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
67
+
68
+ AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
69
+
70
+ It is supported by:
71
+
72
+ - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
73
+ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
74
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
75
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
76
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
77
+
78
+ <!-- description end -->
79
+ <!-- repositories-available start -->
80
+ ## Repositories available
81
+
82
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-AWQ)
83
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GPTQ)
84
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-GGUF)
85
+ * [Unbabel's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1)
86
+ <!-- repositories-available end -->
87
+
88
+ <!-- prompt-template start -->
89
+ ## Prompt template: ChatML
90
+
91
+ ```
92
+ <|im_start|>system
93
+ {system_message}<|im_end|>
94
+ <|im_start|>user
95
+ {prompt}<|im_end|>
96
+ <|im_start|>assistant
97
+
98
+ ```
99
+
100
+ <!-- prompt-template end -->
101
+ <!-- licensing start -->
102
+ ## Licensing
103
+
104
+ The creator of the source model has listed its license as `cc-by-nc-4.0`, and this quantization has therefore used that same license.
105
+
106
+ As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
107
+
108
+ In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Unbabel's TowerInstruct 7B v0.1](https://huggingface.co/Unbabel/TowerInstruct-7B-v0.1).
109
+ <!-- licensing end -->
110
+ <!-- README_AWQ.md-provided-files start -->
111
+ ## Provided files, and AWQ parameters
112
+
113
+ I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
114
+
115
+ Models are released as sharded safetensors files.
116
+
117
+ | Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
118
+ | ------ | ---- | -- | ----------- | ------- | ---- |
119
+ | [main](https://huggingface.co/TheBloke/TowerInstruct-7B-v0.1-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 3.89 GB
120
+
121
+ <!-- README_AWQ.md-provided-files end -->
122
+
123
+ <!-- README_AWQ.md-text-generation-webui start -->
124
+ ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
125
+
126
+ Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
127
+
128
+ It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
129
+
130
+ 1. Click the **Model tab**.
131
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/TowerInstruct-7B-v0.1-AWQ`.
132
+ 3. Click **Download**.
133
+ 4. The model will start downloading. Once it's finished it will say "Done".
134
+ 5. In the top left, click the refresh icon next to **Model**.
135
+ 6. In the **Model** dropdown, choose the model you just downloaded: `TowerInstruct-7B-v0.1-AWQ`
136
+ 7. Select **Loader: AutoAWQ**.
137
+ 8. Click Load, and the model will load and is now ready for use.
138
+ 9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
139
+ 10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
140
+ <!-- README_AWQ.md-text-generation-webui end -->
141
+
142
+ <!-- README_AWQ.md-use-from-vllm start -->
143
+ ## Multi-user inference server: vLLM
144
+
145
+ Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
146
+
147
+ - Please ensure you are using vLLM version 0.2 or later.
148
+ - When using vLLM as a server, pass the `--quantization awq` parameter.
149
+
150
+ For example:
151
+
152
+ ```shell
153
+ python3 -m vllm.entrypoints.api_server --model TheBloke/TowerInstruct-7B-v0.1-AWQ --quantization awq --dtype auto
154
+ ```
155
+
156
+ - When using vLLM from Python code, again set `quantization=awq`.
157
+
158
+ For example:
159
+
160
+ ```python
161
+ from vllm import LLM, SamplingParams
162
+
163
+ prompts = [
164
+ "Tell me about AI",
165
+ "Write a story about llamas",
166
+ "What is 291 - 150?",
167
+ "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
168
+ ]
169
+ prompt_template=f'''<|im_start|>system
170
+ {system_message}<|im_end|>
171
+ <|im_start|>user
172
+ {prompt}<|im_end|>
173
+ <|im_start|>assistant
174
+ '''
175
+
176
+ prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
177
+
178
+ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
179
+
180
+ llm = LLM(model="TheBloke/TowerInstruct-7B-v0.1-AWQ", quantization="awq", dtype="auto")
181
+
182
+ outputs = llm.generate(prompts, sampling_params)
183
+
184
+ # Print the outputs.
185
+ for output in outputs:
186
+ prompt = output.prompt
187
+ generated_text = output.outputs[0].text
188
+ print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
189
+ ```
190
+ <!-- README_AWQ.md-use-from-vllm start -->
191
+
192
+ <!-- README_AWQ.md-use-from-tgi start -->
193
+ ## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
194
+
195
+ Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
196
+
197
+ Example Docker parameters:
198
+
199
+ ```shell
200
+ --model-id TheBloke/TowerInstruct-7B-v0.1-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
201
+ ```
202
+
203
+ Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
204
+
205
+ ```shell
206
+ pip3 install huggingface-hub
207
+ ```
208
+
209
+ ```python
210
+ from huggingface_hub import InferenceClient
211
+
212
+ endpoint_url = "https://your-endpoint-url-here"
213
+
214
+ prompt = "Tell me about AI"
215
+ prompt_template=f'''<|im_start|>system
216
+ {system_message}<|im_end|>
217
+ <|im_start|>user
218
+ {prompt}<|im_end|>
219
+ <|im_start|>assistant
220
+ '''
221
+
222
+ client = InferenceClient(endpoint_url)
223
+ response = client.text_generation(prompt,
224
+ max_new_tokens=128,
225
+ do_sample=True,
226
+ temperature=0.7,
227
+ top_p=0.95,
228
+ top_k=40,
229
+ repetition_penalty=1.1)
230
+
231
+ print(f"Model output: ", response)
232
+ ```
233
+ <!-- README_AWQ.md-use-from-tgi end -->
234
+
235
+ <!-- README_AWQ.md-use-from-python start -->
236
+ ## Inference from Python code using Transformers
237
+
238
+ ### Install the necessary packages
239
+
240
+ - Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
241
+ - Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
242
+
243
+ ```shell
244
+ pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
245
+ ```
246
+
247
+ Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
248
+
249
+ If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
250
+
251
+ ```shell
252
+ pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
253
+ ```
254
+
255
+ If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
256
+
257
+ ```shell
258
+ pip3 uninstall -y autoawq
259
+ git clone https://github.com/casper-hansen/AutoAWQ
260
+ cd AutoAWQ
261
+ pip3 install .
262
+ ```
263
+
264
+ ### Transformers example code (requires Transformers 4.35.0 and later)
265
+
266
+ ```python
267
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
268
+
269
+ model_name_or_path = "TheBloke/TowerInstruct-7B-v0.1-AWQ"
270
+
271
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
272
+ model = AutoModelForCausalLM.from_pretrained(
273
+ model_name_or_path,
274
+ low_cpu_mem_usage=True,
275
+ device_map="cuda:0"
276
+ )
277
+
278
+ # Using the text streamer to stream output one token at a time
279
+ streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
280
+
281
+ prompt = "Tell me about AI"
282
+ prompt_template=f'''<|im_start|>system
283
+ {system_message}<|im_end|>
284
+ <|im_start|>user
285
+ {prompt}<|im_end|>
286
+ <|im_start|>assistant
287
+ '''
288
+
289
+ # Convert prompt to tokens
290
+ tokens = tokenizer(
291
+ prompt_template,
292
+ return_tensors='pt'
293
+ ).input_ids.cuda()
294
+
295
+ generation_params = {
296
+ "do_sample": True,
297
+ "temperature": 0.7,
298
+ "top_p": 0.95,
299
+ "top_k": 40,
300
+ "max_new_tokens": 512,
301
+ "repetition_penalty": 1.1
302
+ }
303
+
304
+ # Generate streamed output, visible one token at a time
305
+ generation_output = model.generate(
306
+ tokens,
307
+ streamer=streamer,
308
+ **generation_params
309
+ )
310
+
311
+ # Generation without a streamer, which will include the prompt in the output
312
+ generation_output = model.generate(
313
+ tokens,
314
+ **generation_params
315
+ )
316
+
317
+ # Get the tokens from the output, decode them, print them
318
+ token_output = generation_output[0]
319
+ text_output = tokenizer.decode(token_output)
320
+ print("model.generate output: ", text_output)
321
+
322
+ # Inference is also possible via Transformers' pipeline
323
+ from transformers import pipeline
324
+
325
+ pipe = pipeline(
326
+ "text-generation",
327
+ model=model,
328
+ tokenizer=tokenizer,
329
+ **generation_params
330
+ )
331
+
332
+ pipe_output = pipe(prompt_template)[0]['generated_text']
333
+ print("pipeline output: ", pipe_output)
334
+
335
+ ```
336
+ <!-- README_AWQ.md-use-from-python end -->
337
+
338
+ <!-- README_AWQ.md-compatibility start -->
339
+ ## Compatibility
340
+
341
+ The files provided are tested to work with:
342
+
343
+ - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
344
+ - [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
345
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
346
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
347
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
348
+
349
+ <!-- README_AWQ.md-compatibility end -->
350
+
351
+ <!-- footer start -->
352
+ <!-- 200823 -->
353
+ ## Discord
354
+
355
+ For further support, and discussions on these models and AI in general, join us at:
356
+
357
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
358
+
359
+ ## Thanks, and how to contribute
360
+
361
+ Thanks to the [chirper.ai](https://chirper.ai) team!
362
+
363
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
364
+
365
+ 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.
366
+
367
+ 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.
368
+
369
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
370
+
371
+ * Patreon: https://patreon.com/TheBlokeAI
372
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
373
+
374
+ **Special thanks to**: Aemon Algiz.
375
+
376
+ **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
377
+
378
+
379
+ Thank you to all my generous patrons and donaters!
380
+
381
+ And thank you again to a16z for their generous grant.
382
+
383
+ <!-- footer end -->
384
+
385
+ # Original model card: Unbabel's TowerInstruct 7B v0.1
386
+
387
+ # Model Card for TowerInstruct-7B-v0.1
388
+
389
+ ## Model Details
390
+
391
+ ### Model Description
392
+
393
+ TowerInstruct-7B is a language model that results from fine-tuning TowerBase on the TowerBlocks supervised fine-tuning dataset. TowerInstruct-7B-v0.1 is the first model in the series.
394
+ The model is trained to handle several translation-related tasks, such as general machine translation (e.g., sentence- and document-level translation, terminology-aware translation, context-aware translation), automatic post edition, named-entity recognition, gramatical error correction, and paraphrase generation.
395
+ We will release more details in the upcoming technical report.
396
+
397
+ - **Developed by:** Unbabel, Instituto Superior Técnico, CentraleSupélec University of Paris-Saclay
398
+ - **Model type:** A 7B parameter model fine-tuned on a mix of publicly available, synthetic datasets on translation-related tasks, as well as conversational datasets and code instructions.
399
+ - **Language(s) (NLP):** English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, Russian
400
+ - **License:** CC-BY-NC-4.0, Llama 2 is licensed under the [LLAMA 2 Community License](https://ai.meta.com/llama/license/), Copyright © Meta Platforms, Inc. All Rights Reserved.
401
+ - **Finetuned from model:** [TowerBase](https://huggingface.co/Unbabel/TowerBase-7B-v0.1)
402
+
403
+ ## Intended uses & limitations
404
+
405
+ The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset ([TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1)), which contains a diverse range of data sources:
406
+ - Translation
407
+ - Automatic Post Edition
408
+ - Machine Translation Evaluation
409
+ - Context-aware Translation
410
+ - Terminology-aware Translation
411
+ - Multi-reference Translation
412
+ - Named-entity Recognition
413
+ - Paraphrase Generation
414
+ - Synthetic Chat data
415
+ - Code instructions
416
+
417
+ You can find the dataset and all data sources of [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1) here.
418
+
419
+ Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
420
+
421
+ ```python
422
+ # Install transformers from source - only needed for versions <= v4.34
423
+ # pip install git+https://github.com/huggingface/transformers.git
424
+ # pip install accelerate
425
+
426
+ import torch
427
+ from transformers import pipeline
428
+
429
+ pipe = pipeline("text-generation", model="Unbabel/TowerInstruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")
430
+ # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
431
+ messages = [
432
+ {"role": "user", "content": "Translate the following text from Portuguese into English.\nPortuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.\nEnglish:"},
433
+ ]
434
+ prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
435
+ outputs = pipe(prompt, max_new_tokens=256, do_sample=False)
436
+ print(outputs[0]["generated_text"])
437
+ # <|im_start|>user
438
+ # Translate the following text from Portuguese into English.
439
+ # Portuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.
440
+ # English:<|im_end|>
441
+ # <|im_start|>assistant
442
+ # A group of researchers has launched a new model for translation-related tasks.
443
+ ```
444
+
445
+ ### Out-of-Scope Use
446
+
447
+ The model is not guaranteed to perform for languages other than the 10 languages it supports. Even though we trained the model on conversational data and code instructions, it is not intended to be used as a conversational chatbot or code assistant.
448
+
449
+ ## Bias, Risks, and Limitations
450
+
451
+ TowerInstruct-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
452
+
453
+ ## Prompt Format
454
+
455
+ TowerInstruct-v0.1 was trained using the ChatML prompt templates without any system prompts. An example follows below:
456
+ ```
457
+ <|im_start|>user
458
+ {USER PROMPT}<|im_end|>
459
+ <|im_start|>assistant
460
+ {MODEL RESPONSE}<|im_end|>
461
+ <|im_start|>user
462
+ [...]
463
+ ```
464
+
465
+ ### Supervised tasks
466
+
467
+ The prompts for all supervised tasks can be found in [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1). We have used multiple prompt templates for each task. While different prompts may offer different outputs, the difference in downstream performance should be very minimal.
468
+
469
+ ## Training Details
470
+
471
+ ### Training Data
472
+
473
+ Link to [TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1).
474
+
475
+ #### Training Hyperparameters
476
+
477
+ The following hyperparameters were used during training:
478
+
479
+ - total_train_batch_size: 256
480
+
481
+ - learning_rate: 7e-06
482
+
483
+ - lr_scheduler_type: cosine
484
+
485
+ - lr_scheduler_warmup_steps: 500
486
+
487
+ - weight_decay: 0.01
488
+
489
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
490
+
491
+ - num_epochs: 4
492
+
493
+ - max_seq_length: 2048
494
+
495
+ ## Citation
496
+
497
+ To be completed.
498
+
499
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)