TheBloke commited on
Commit
10f6255
1 Parent(s): a48997a

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +404 -0
README.md ADDED
@@ -0,0 +1,404 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Intel/neural-chat-7b-v3-1
3
+ inference: false
4
+ license: apache-2.0
5
+ model_creator: Intel
6
+ model_name: Neural Chat 7B v3-1
7
+ model_type: mistral
8
+ prompt_template: '{prompt}
9
+
10
+ '
11
+ quantized_by: TheBloke
12
+ ---
13
+ <!-- markdownlint-disable MD041 -->
14
+
15
+ <!-- header start -->
16
+ <!-- 200823 -->
17
+ <div style="width: auto; margin-left: auto; margin-right: auto">
18
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
+ </div>
20
+ <div style="display: flex; justify-content: space-between; width: 100%;">
21
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
22
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
23
+ </div>
24
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
25
+ <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>
26
+ </div>
27
+ </div>
28
+ <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>
29
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
30
+ <!-- header end -->
31
+
32
+ # Neural Chat 7B v3-1 - AWQ
33
+ - Model creator: [Intel](https://huggingface.co/Intel)
34
+ - Original model: [Neural Chat 7B v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1)
35
+
36
+ <!-- description start -->
37
+ ## Description
38
+
39
+ This repo contains AWQ model files for [Intel's Neural Chat 7B v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1).
40
+
41
+ These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
42
+
43
+
44
+ ### About AWQ
45
+
46
+ 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.
47
+
48
+ It is supported by:
49
+
50
+ - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
51
+ - [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
52
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
53
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
54
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
55
+
56
+ <!-- description end -->
57
+ <!-- repositories-available start -->
58
+ ## Repositories available
59
+
60
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/neural-chat-7B-v3-1-AWQ)
61
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/neural-chat-7B-v3-1-GPTQ)
62
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/neural-chat-7B-v3-1-GGUF)
63
+ * [Intel's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Intel/neural-chat-7b-v3-1)
64
+ <!-- repositories-available end -->
65
+
66
+ <!-- prompt-template start -->
67
+ ## Prompt template: Unknown
68
+
69
+ ```
70
+ {prompt}
71
+
72
+ ```
73
+
74
+ <!-- prompt-template end -->
75
+
76
+
77
+ <!-- README_AWQ.md-provided-files start -->
78
+ ## Provided files, and AWQ parameters
79
+
80
+ I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
81
+
82
+ Models are released as sharded safetensors files.
83
+
84
+ | Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
85
+ | ------ | ---- | -- | ----------- | ------- | ---- |
86
+ | [main](https://huggingface.co/TheBloke/neural-chat-7B-v3-1-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 4.15 GB
87
+
88
+ <!-- README_AWQ.md-provided-files end -->
89
+
90
+ <!-- README_AWQ.md-text-generation-webui start -->
91
+ ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
92
+
93
+ Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
94
+
95
+ 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.
96
+
97
+ 1. Click the **Model tab**.
98
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/neural-chat-7B-v3-1-AWQ`.
99
+ 3. Click **Download**.
100
+ 4. The model will start downloading. Once it's finished it will say "Done".
101
+ 5. In the top left, click the refresh icon next to **Model**.
102
+ 6. In the **Model** dropdown, choose the model you just downloaded: `neural-chat-7B-v3-1-AWQ`
103
+ 7. Select **Loader: AutoAWQ**.
104
+ 8. Click Load, and the model will load and is now ready for use.
105
+ 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.
106
+ 10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
107
+ <!-- README_AWQ.md-text-generation-webui end -->
108
+
109
+ <!-- README_AWQ.md-use-from-vllm start -->
110
+ ## Multi-user inference server: vLLM
111
+
112
+ Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
113
+
114
+ - Please ensure you are using vLLM version 0.2 or later.
115
+ - When using vLLM as a server, pass the `--quantization awq` parameter.
116
+
117
+ For example:
118
+
119
+ ```shell
120
+ python3 -m vllm.entrypoints.api_server --model TheBloke/neural-chat-7B-v3-1-AWQ --quantization awq --dtype auto
121
+ ```
122
+
123
+ - When using vLLM from Python code, again set `quantization=awq`.
124
+
125
+ For example:
126
+
127
+ ```python
128
+ from vllm import LLM, SamplingParams
129
+
130
+ prompts = [
131
+ "Tell me about AI",
132
+ "Write a story about llamas",
133
+ "What is 291 - 150?",
134
+ "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
135
+ ]
136
+ prompt_template=f'''{prompt}
137
+ '''
138
+
139
+ prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
140
+
141
+ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
142
+
143
+ llm = LLM(model="TheBloke/neural-chat-7B-v3-1-AWQ", quantization="awq", dtype="auto")
144
+
145
+ outputs = llm.generate(prompts, sampling_params)
146
+
147
+ # Print the outputs.
148
+ for output in outputs:
149
+ prompt = output.prompt
150
+ generated_text = output.outputs[0].text
151
+ print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
152
+ ```
153
+ <!-- README_AWQ.md-use-from-vllm start -->
154
+
155
+ <!-- README_AWQ.md-use-from-tgi start -->
156
+ ## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
157
+
158
+ Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
159
+
160
+ Example Docker parameters:
161
+
162
+ ```shell
163
+ --model-id TheBloke/neural-chat-7B-v3-1-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
164
+ ```
165
+
166
+ Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
167
+
168
+ ```shell
169
+ pip3 install huggingface-hub
170
+ ```
171
+
172
+ ```python
173
+ from huggingface_hub import InferenceClient
174
+
175
+ endpoint_url = "https://your-endpoint-url-here"
176
+
177
+ prompt = "Tell me about AI"
178
+ prompt_template=f'''{prompt}
179
+ '''
180
+
181
+ client = InferenceClient(endpoint_url)
182
+ response = client.text_generation(prompt,
183
+ max_new_tokens=128,
184
+ do_sample=True,
185
+ temperature=0.7,
186
+ top_p=0.95,
187
+ top_k=40,
188
+ repetition_penalty=1.1)
189
+
190
+ print(f"Model output: ", response)
191
+ ```
192
+ <!-- README_AWQ.md-use-from-tgi end -->
193
+
194
+ <!-- README_AWQ.md-use-from-python start -->
195
+ ## Inference from Python code using Transformers
196
+
197
+ ### Install the necessary packages
198
+
199
+ - Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
200
+ - Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
201
+
202
+ ```shell
203
+ pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
204
+ ```
205
+
206
+ Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
207
+
208
+ If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
209
+
210
+ ```shell
211
+ pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
212
+ ```
213
+
214
+ If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
215
+
216
+ ```shell
217
+ pip3 uninstall -y autoawq
218
+ git clone https://github.com/casper-hansen/AutoAWQ
219
+ cd AutoAWQ
220
+ pip3 install .
221
+ ```
222
+
223
+ ### Transformers example code (requires Transformers 4.35.0 and later)
224
+
225
+ ```python
226
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
227
+
228
+ model_name_or_path = "TheBloke/neural-chat-7B-v3-1-AWQ"
229
+
230
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
231
+ model = AutoModelForCausalLM.from_pretrained(
232
+ model_name_or_path,
233
+ low_cpu_mem_usage=True,
234
+ device_map="cuda:0"
235
+ )
236
+
237
+ # Using the text streamer to stream output one token at a time
238
+ streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
239
+
240
+ prompt = "Tell me about AI"
241
+ prompt_template=f'''{prompt}
242
+ '''
243
+
244
+ # Convert prompt to tokens
245
+ tokens = tokenizer(
246
+ prompt_template,
247
+ return_tensors='pt'
248
+ ).input_ids.cuda()
249
+
250
+ generation_params = {
251
+ "do_sample": True,
252
+ "temperature": 0.7,
253
+ "top_p": 0.95,
254
+ "top_k": 40,
255
+ "max_new_tokens": 512,
256
+ "repetition_penalty": 1.1
257
+ }
258
+
259
+ # Generate streamed output, visible one token at a time
260
+ generation_output = model.generate(
261
+ tokens,
262
+ streamer=streamer,
263
+ **generation_params
264
+ )
265
+
266
+ # Generation without a streamer, which will include the prompt in the output
267
+ generation_output = model.generate(
268
+ tokens,
269
+ **generation_params
270
+ )
271
+
272
+ # Get the tokens from the output, decode them, print them
273
+ token_output = generation_output[0]
274
+ text_output = tokenizer.decode(token_output)
275
+ print("model.generate output: ", text_output)
276
+
277
+ # Inference is also possible via Transformers' pipeline
278
+ from transformers import pipeline
279
+
280
+ pipe = pipeline(
281
+ "text-generation",
282
+ model=model,
283
+ tokenizer=tokenizer,
284
+ **generation_params
285
+ )
286
+
287
+ pipe_output = pipe(prompt_template)[0]['generated_text']
288
+ print("pipeline output: ", pipe_output)
289
+
290
+ ```
291
+ <!-- README_AWQ.md-use-from-python end -->
292
+
293
+ <!-- README_AWQ.md-compatibility start -->
294
+ ## Compatibility
295
+
296
+ The files provided are tested to work with:
297
+
298
+ - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
299
+ - [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
300
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
301
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
302
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
303
+
304
+ <!-- README_AWQ.md-compatibility end -->
305
+
306
+ <!-- footer start -->
307
+ <!-- 200823 -->
308
+ ## Discord
309
+
310
+ For further support, and discussions on these models and AI in general, join us at:
311
+
312
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
313
+
314
+ ## Thanks, and how to contribute
315
+
316
+ Thanks to the [chirper.ai](https://chirper.ai) team!
317
+
318
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
319
+
320
+ 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.
321
+
322
+ 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.
323
+
324
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
325
+
326
+ * Patreon: https://patreon.com/TheBlokeAI
327
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
328
+
329
+ **Special thanks to**: Aemon Algiz.
330
+
331
+ **Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
332
+
333
+
334
+ Thank you to all my generous patrons and donaters!
335
+
336
+ And thank you again to a16z for their generous grant.
337
+
338
+ <!-- footer end -->
339
+
340
+ # Original model card: Intel's Neural Chat 7B v3-1
341
+
342
+
343
+ ## Finetuning on [habana](https://habana.ai/) HPU
344
+
345
+ This model is a fine-tuned model based on [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the open source dataset [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca). Then we align it with DPO algorithm. For more details, you can refer our blog: [NeuralChat: Simplifying Supervised Instruction Fine-Tuning and Reinforcement Aligning](https://medium.com/intel-analytics-software/neuralchat-simplifying-supervised-instruction-fine-tuning-and-reinforcement-aligning-for-chatbots-d034bca44f69) and [The Practice of Supervised Fine-tuning and Direct Preference Optimization on Habana Gaudi2](https://medium.com/@NeuralCompressor/the-practice-of-supervised-finetuning-and-direct-preference-optimization-on-habana-gaudi2-a1197d8a3cd3).
346
+
347
+ ## Model date
348
+ Neural-chat-7b-v3-1 was trained between September and October, 2023.
349
+
350
+ ## Evaluation
351
+
352
+ We submit our model to [open_llm_leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard), and the model performance has been **improved significantly** as we see from the average metric of 7 tasks from the leaderboard.
353
+
354
+ | Model | Average ⬆️| ARC (25-s) ⬆️ | HellaSwag (10-s) ⬆️ | MMLU (5-s) ⬆️| TruthfulQA (MC) (0-s) ⬆️ | Winogrande (5-s) | GSM8K (5-s) | DROP (3-s) |
355
+ | --- | --- | --- | --- | --- | --- | --- | --- | --- |
356
+ |[mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) | 50.32 | 59.58 | 83.31 | 64.16 | 42.15 | 78.37 | 18.12 | 6.14 |
357
+ | [Intel/neural-chat-7b-v3](https://huggingface.co/Intel/neural-chat-7b-v3) | **57.31** | 67.15 | 83.29 | 62.26 | 58.77 | 78.06 | 1.21 | 50.43 |
358
+ | [Intel/neural-chat-7b-v3-1](https://huggingface.co/Intel/neural-chat-7b-v3-1) | **59.06** | 66.21 | 83.64 | 62.37 | 59.65 | 78.14 | 19.56 | 43.84 |
359
+
360
+ ## Training procedure
361
+
362
+ ### Training hyperparameters
363
+
364
+ The following hyperparameters were used during training:
365
+ - learning_rate: 1e-04
366
+ - train_batch_size: 1
367
+ - eval_batch_size: 2
368
+ - seed: 42
369
+ - distributed_type: multi-HPU
370
+ - num_devices: 8
371
+ - gradient_accumulation_steps: 8
372
+ - total_train_batch_size: 64
373
+ - total_eval_batch_size: 8
374
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
375
+ - lr_scheduler_type: linear
376
+ - lr_scheduler_warmup_ratio: 0.02
377
+ - num_epochs: 2.0
378
+
379
+ ## Inference with transformers
380
+
381
+ ```shell
382
+ import transformers
383
+ model = transformers.AutoModelForCausalLM.from_pretrained(
384
+ 'Intel/neural-chat-7b-v3-1'
385
+ )
386
+ ```
387
+
388
+ ## Ethical Considerations and Limitations
389
+ neural-chat-7b-v3-1 can produce factually incorrect output, and should not be relied on to produce factually accurate information. neural-chat-7b-v3-1 was trained on [Open-Orca/SlimOrca](https://huggingface.co/datasets/Open-Orca/SlimOrca) based on [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1). Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
390
+
391
+ Therefore, before deploying any applications of neural-chat-7b-v3-1, developers should perform safety testing.
392
+
393
+ ## Disclaimer
394
+
395
+ The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
396
+
397
+ ## Organizations developing the model
398
+
399
+ The NeuralChat team with members from Intel/SATG/AIA/AIPT. Core team members: Kaokao Lv, Liang Lv, Chang Wang, Wenxin Zhang, Xuhui Ren, and Haihao Shen.
400
+
401
+ ## Useful links
402
+ * Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
403
+ * Intel Extension for Transformers [link](https://github.com/intel/intel-extension-for-transformers)
404
+ * Intel Extension for PyTorch [link](https://github.com/intel/intel-extension-for-pytorch)