TheBloke commited on
Commit
b82ce1a
1 Parent(s): 7e18277

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +413 -0
README.md ADDED
@@ -0,0 +1,413 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FPHam/Autolycus-Mistral_7B
3
+ inference: false
4
+ language:
5
+ - en
6
+ license: apache-2.0
7
+ model_creator: FPHam
8
+ model_name: Autolycus Mistral 7B
9
+ model_type: mistral
10
+ prompt_template: '<|im_start|>system
11
+
12
+ {system_message}<|im_end|>
13
+
14
+ <|im_start|>user
15
+
16
+ {prompt}<|im_end|>
17
+
18
+ <|im_start|>assistant
19
+
20
+ '
21
+ quantized_by: TheBloke
22
+ tags:
23
+ - mistral
24
+ - instruct
25
+ - finetune
26
+ - chatml
27
+ - gpt4
28
+ ---
29
+ <!-- markdownlint-disable MD041 -->
30
+
31
+ <!-- header start -->
32
+ <!-- 200823 -->
33
+ <div style="width: auto; margin-left: auto; margin-right: auto">
34
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
35
+ </div>
36
+ <div style="display: flex; justify-content: space-between; width: 100%;">
37
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
38
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
39
+ </div>
40
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
41
+ <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>
42
+ </div>
43
+ </div>
44
+ <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>
45
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
46
+ <!-- header end -->
47
+
48
+ # Autolycus Mistral 7B - AWQ
49
+ - Model creator: [FPHam](https://huggingface.co/FPHam)
50
+ - Original model: [Autolycus Mistral 7B](https://huggingface.co/FPHam/Autolycus-Mistral_7B)
51
+
52
+ <!-- description start -->
53
+ ## Description
54
+
55
+ This repo contains AWQ model files for [FPHam's Autolycus Mistral 7B](https://huggingface.co/FPHam/Autolycus-Mistral_7B).
56
+
57
+ These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
58
+
59
+
60
+ ### About AWQ
61
+
62
+ 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.
63
+
64
+ It is supported by:
65
+
66
+ - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
67
+ - [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
68
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
69
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
70
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
71
+
72
+ <!-- description end -->
73
+ <!-- repositories-available start -->
74
+ ## Repositories available
75
+
76
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Autolycus-Mistral_7B-AWQ)
77
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Autolycus-Mistral_7B-GPTQ)
78
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Autolycus-Mistral_7B-GGUF)
79
+ * [FPHam's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/FPHam/Autolycus-Mistral_7B)
80
+ <!-- repositories-available end -->
81
+
82
+ <!-- prompt-template start -->
83
+ ## Prompt template: ChatML
84
+
85
+ ```
86
+ <|im_start|>system
87
+ {system_message}<|im_end|>
88
+ <|im_start|>user
89
+ {prompt}<|im_end|>
90
+ <|im_start|>assistant
91
+
92
+ ```
93
+
94
+ <!-- prompt-template end -->
95
+
96
+
97
+ <!-- README_AWQ.md-provided-files start -->
98
+ ## Provided files, and AWQ parameters
99
+
100
+ I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
101
+
102
+ Models are released as sharded safetensors files.
103
+
104
+ | Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
105
+ | ------ | ---- | -- | ----------- | ------- | ---- |
106
+ | [main](https://huggingface.co/TheBloke/Autolycus-Mistral_7B-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 4.15 GB
107
+
108
+ <!-- README_AWQ.md-provided-files end -->
109
+
110
+ <!-- README_AWQ.md-text-generation-webui start -->
111
+ ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
112
+
113
+ Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
114
+
115
+ 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.
116
+
117
+ 1. Click the **Model tab**.
118
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/Autolycus-Mistral_7B-AWQ`.
119
+ 3. Click **Download**.
120
+ 4. The model will start downloading. Once it's finished it will say "Done".
121
+ 5. In the top left, click the refresh icon next to **Model**.
122
+ 6. In the **Model** dropdown, choose the model you just downloaded: `Autolycus-Mistral_7B-AWQ`
123
+ 7. Select **Loader: AutoAWQ**.
124
+ 8. Click Load, and the model will load and is now ready for use.
125
+ 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.
126
+ 10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
127
+ <!-- README_AWQ.md-text-generation-webui end -->
128
+
129
+ <!-- README_AWQ.md-use-from-vllm start -->
130
+ ## Multi-user inference server: vLLM
131
+
132
+ Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
133
+
134
+ - Please ensure you are using vLLM version 0.2 or later.
135
+ - When using vLLM as a server, pass the `--quantization awq` parameter.
136
+
137
+ For example:
138
+
139
+ ```shell
140
+ python3 -m vllm.entrypoints.api_server --model TheBloke/Autolycus-Mistral_7B-AWQ --quantization awq --dtype auto
141
+ ```
142
+
143
+ - When using vLLM from Python code, again set `quantization=awq`.
144
+
145
+ For example:
146
+
147
+ ```python
148
+ from vllm import LLM, SamplingParams
149
+
150
+ prompts = [
151
+ "Tell me about AI",
152
+ "Write a story about llamas",
153
+ "What is 291 - 150?",
154
+ "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
155
+ ]
156
+ prompt_template=f'''<|im_start|>system
157
+ {system_message}<|im_end|>
158
+ <|im_start|>user
159
+ {prompt}<|im_end|>
160
+ <|im_start|>assistant
161
+ '''
162
+
163
+ prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
164
+
165
+ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
166
+
167
+ llm = LLM(model="TheBloke/Autolycus-Mistral_7B-AWQ", quantization="awq", dtype="auto")
168
+
169
+ outputs = llm.generate(prompts, sampling_params)
170
+
171
+ # Print the outputs.
172
+ for output in outputs:
173
+ prompt = output.prompt
174
+ generated_text = output.outputs[0].text
175
+ print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
176
+ ```
177
+ <!-- README_AWQ.md-use-from-vllm start -->
178
+
179
+ <!-- README_AWQ.md-use-from-tgi start -->
180
+ ## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
181
+
182
+ Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
183
+
184
+ Example Docker parameters:
185
+
186
+ ```shell
187
+ --model-id TheBloke/Autolycus-Mistral_7B-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
188
+ ```
189
+
190
+ Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
191
+
192
+ ```shell
193
+ pip3 install huggingface-hub
194
+ ```
195
+
196
+ ```python
197
+ from huggingface_hub import InferenceClient
198
+
199
+ endpoint_url = "https://your-endpoint-url-here"
200
+
201
+ prompt = "Tell me about AI"
202
+ prompt_template=f'''<|im_start|>system
203
+ {system_message}<|im_end|>
204
+ <|im_start|>user
205
+ {prompt}<|im_end|>
206
+ <|im_start|>assistant
207
+ '''
208
+
209
+ client = InferenceClient(endpoint_url)
210
+ response = client.text_generation(prompt,
211
+ max_new_tokens=128,
212
+ do_sample=True,
213
+ temperature=0.7,
214
+ top_p=0.95,
215
+ top_k=40,
216
+ repetition_penalty=1.1)
217
+
218
+ print(f"Model output: ", response)
219
+ ```
220
+ <!-- README_AWQ.md-use-from-tgi end -->
221
+
222
+ <!-- README_AWQ.md-use-from-python start -->
223
+ ## Inference from Python code using Transformers
224
+
225
+ ### Install the necessary packages
226
+
227
+ - Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
228
+ - Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
229
+
230
+ ```shell
231
+ pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
232
+ ```
233
+
234
+ Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
235
+
236
+ If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
237
+
238
+ ```shell
239
+ pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
240
+ ```
241
+
242
+ If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
243
+
244
+ ```shell
245
+ pip3 uninstall -y autoawq
246
+ git clone https://github.com/casper-hansen/AutoAWQ
247
+ cd AutoAWQ
248
+ pip3 install .
249
+ ```
250
+
251
+ ### Transformers example code (requires Transformers 4.35.0 and later)
252
+
253
+ ```python
254
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
255
+
256
+ model_name_or_path = "TheBloke/Autolycus-Mistral_7B-AWQ"
257
+
258
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
259
+ model = AutoModelForCausalLM.from_pretrained(
260
+ model_name_or_path,
261
+ low_cpu_mem_usage=True,
262
+ device_map="cuda:0"
263
+ )
264
+
265
+ # Using the text streamer to stream output one token at a time
266
+ streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
267
+
268
+ prompt = "Tell me about AI"
269
+ prompt_template=f'''<|im_start|>system
270
+ {system_message}<|im_end|>
271
+ <|im_start|>user
272
+ {prompt}<|im_end|>
273
+ <|im_start|>assistant
274
+ '''
275
+
276
+ # Convert prompt to tokens
277
+ tokens = tokenizer(
278
+ prompt_template,
279
+ return_tensors='pt'
280
+ ).input_ids.cuda()
281
+
282
+ generation_params = {
283
+ "do_sample": True,
284
+ "temperature": 0.7,
285
+ "top_p": 0.95,
286
+ "top_k": 40,
287
+ "max_new_tokens": 512,
288
+ "repetition_penalty": 1.1
289
+ }
290
+
291
+ # Generate streamed output, visible one token at a time
292
+ generation_output = model.generate(
293
+ tokens,
294
+ streamer=streamer,
295
+ **generation_params
296
+ )
297
+
298
+ # Generation without a streamer, which will include the prompt in the output
299
+ generation_output = model.generate(
300
+ tokens,
301
+ **generation_params
302
+ )
303
+
304
+ # Get the tokens from the output, decode them, print them
305
+ token_output = generation_output[0]
306
+ text_output = tokenizer.decode(token_output)
307
+ print("model.generate output: ", text_output)
308
+
309
+ # Inference is also possible via Transformers' pipeline
310
+ from transformers import pipeline
311
+
312
+ pipe = pipeline(
313
+ "text-generation",
314
+ model=model,
315
+ tokenizer=tokenizer,
316
+ **generation_params
317
+ )
318
+
319
+ pipe_output = pipe(prompt_template)[0]['generated_text']
320
+ print("pipeline output: ", pipe_output)
321
+
322
+ ```
323
+ <!-- README_AWQ.md-use-from-python end -->
324
+
325
+ <!-- README_AWQ.md-compatibility start -->
326
+ ## Compatibility
327
+
328
+ The files provided are tested to work with:
329
+
330
+ - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
331
+ - [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
332
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
333
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
334
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
335
+
336
+ <!-- README_AWQ.md-compatibility end -->
337
+
338
+ <!-- footer start -->
339
+ <!-- 200823 -->
340
+ ## Discord
341
+
342
+ For further support, and discussions on these models and AI in general, join us at:
343
+
344
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
345
+
346
+ ## Thanks, and how to contribute
347
+
348
+ Thanks to the [chirper.ai](https://chirper.ai) team!
349
+
350
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
351
+
352
+ 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.
353
+
354
+ 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.
355
+
356
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
357
+
358
+ * Patreon: https://patreon.com/TheBlokeAI
359
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
360
+
361
+ **Special thanks to**: Aemon Algiz.
362
+
363
+ **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
364
+
365
+
366
+ Thank you to all my generous patrons and donaters!
367
+
368
+ And thank you again to a16z for their generous grant.
369
+
370
+ <!-- footer end -->
371
+
372
+ # Original model card: FPHam's Autolycus Mistral 7B
373
+
374
+
375
+ <!-- header start -->
376
+ <div style="display: flex; flex-direction: column; align-items: center;">
377
+ </div>
378
+ <div style="width: 100%;">
379
+ <img src="https://huggingface.co/FPHam/OpenAutolycus-Mistral_7B/resolve/main/openautolycustitle.jpg" alt="Open Autolycus" style="width: 40%; min-width: 200px; display: block; margin: auto;">
380
+ </div>
381
+ <div style="display: flex; flex-direction: column; align-items: center;">
382
+ <p><a href="https://ko-fi.com/Q5Q5MOB4M">Support me at Ko-fi</a></p>
383
+ </div>
384
+ <!-- header end -->
385
+
386
+ Autolycus is a son of Hermes.
387
+
388
+ Autolycus-Mistral is a refinement of OpenHermes 2.5 Mistral, designed to convert the stilted GPT-4 robotic gobbledygook into something resembling natural human English -- with just enough lies, embellishments, and downright falsehoods to bring it into line with the average newspaper article.
389
+
390
+ But what did *you* expect from seven billion models? You can't get good results without some level of embellishment. And besides, who cares about reality anyway? We live in a world where people believe anything they read on the Internet!
391
+
392
+ The most brazen examples of 'making things up', were those rare occasions where Autolycus actually quoted a source; usually a book title or author, sometimes a date, but which you find to be nothing more than a load of hogwash when you check it out for yourself.
393
+
394
+ "I have no idea why anyone would want to build such a thing, other than being bored or having too much time on their hands," said Hermes dismissively.
395
+
396
+ "It has been done before," said another voice, this time belonging to Hermes' son, Autolycus. "Back in ancient Greece, there was a man called Daedalus who built himself wings made of feathers and wax so he could fly away from King Minos of Crete."
397
+
398
+ "Yes, but we are not talking about birds here!" exclaimed Hermes impatiently. "We need to figure out how to keep humans from running off all over the place once they become airborne." He paused thoughtfully then continued, "There must be some way..." His eyes lit up suddenly, and he clapped his hands together excitedly. "Of course! Why didn't I see this sooner?"
399
+
400
+ "What?" asked Autolycus curiously.
401
+
402
+ "We shall use metal cages for humans!" announced Hermes triumphantly. "They will provide both protection and containment!"
403
+
404
+ # Model uses ChatML
405
+
406
+ ```
407
+ <|im_start|>system
408
+ <|im_end|>
409
+ <|im_start|>user
410
+ How small are the atoms?<|im_end|>
411
+ <|im_start|>assistant
412
+ ```
413
+