File size: 17,498 Bytes
8edfb1e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
base_model: ehartford/dolphin-2.1-mistral-7b
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
inference: false
language:
- en
license: apache-2.0
model_creator: Eric Hartford
model_name: Dolphin 2.1 Mistral 7B
model_type: mistral
prompt_template: '<|im_start|>system

  {system_message}<|im_end|>

  <|im_start|>user

  {prompt}<|im_end|>

  <|im_start|>assistant

  '
quantized_by: TheBloke
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <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>
    </div>
</div>
<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>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Dolphin 2.1 Mistral 7B - AWQ
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Dolphin 2.1 Mistral 7B](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)

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

This repo contains AWQ model files for [Eric Hartford's Dolphin 2.1 Mistral 7B](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b).


### About AWQ

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.

It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.

As of September 25th 2023, preliminary Llama-only AWQ support has also been added to [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference).

Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available

* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)
<!-- repositories-available end -->

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

```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

```

<!-- prompt-template end -->


<!-- README_AWQ.md-provided-files start -->
## Provided files, and AWQ parameters

For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.

Models are released as sharded safetensors files.

| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.15 GB

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

<!-- README_AWQ.md-use-from-vllm start -->
## Serving this model from vLLM

Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).

Note: at the time of writing, vLLM has not yet done a new release with AWQ support.

If you try the vLLM examples below and get an error about `quantization` being unrecognised, or other AWQ-related issues, please install vLLM from Github source.

- When using vLLM as a server, pass the `--quantization awq` parameter, for example:

```shell
python3 python -m vllm.entrypoints.api_server --model TheBloke/dolphin-2.1-mistral-7B-AWQ --quantization awq --dtype half
```

When using vLLM from Python code, pass the `quantization=awq` parameter, for example:

```python
from vllm import LLM, SamplingParams

prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="TheBloke/dolphin-2.1-mistral-7B-AWQ", quantization="awq", dtype="half")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
<!-- README_AWQ.md-use-from-vllm start -->

<!-- README_AWQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)

Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`

Example Docker parameters:

```shell
--model-id TheBloke/dolphin-2.1-mistral-7B-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```

Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):

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

```python
from huggingface_hub import InferenceClient

endpoint_url = "https://your-endpoint-url-here"

prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

'''

client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
                                  max_new_tokens=128,
                                  do_sample=True,
                                  temperature=0.7,
                                  top_p=0.95,
                                  top_k=40,
                                  repetition_penalty=1.1)

print(f"Model output: {response}")
```
<!-- README_AWQ.md-use-from-tgi end -->

<!-- README_AWQ.md-use-from-python start -->
## How to use this AWQ model from Python code

### Install the necessary packages

Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later

```shell
pip3 install autoawq
```

If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:

```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```

### You can then try the following example code

```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_name_or_path = "TheBloke/dolphin-2.1-mistral-7B-AWQ"

# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
                                          trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)

prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

'''

print("\n\n*** Generate:")

tokens = tokenizer(
    prompt_template,
    return_tensors='pt'
).input_ids.cuda()

# Generate output
generation_output = model.generate(
    tokens,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    max_new_tokens=512
)

print("Output: ", tokenizer.decode(generation_output[0]))

"""
# Inference should be possible with transformers pipeline as well in future
# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
from transformers import pipeline

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.95,
    top_k=40,
    repetition_penalty=1.1
)

print(pipe(prompt_template)[0]['generated_text'])
"""
```
<!-- README_AWQ.md-use-from-python end -->

<!-- README_AWQ.md-compatibility start -->
## Compatibility

The files provided are tested to work with:

- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
- [vLLM](https://github.com/vllm-project/vllm)
- [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)

TGI merged AWQ support on September 25th, 2023: [TGI PR #1054](https://github.com/huggingface/text-generation-inference/pull/1054).  Use the `:latest` Docker container until the next TGI release is made.

<!-- README_AWQ.md-compatibility end -->

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

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

[TheBloke AI's Discord server](https://discord.gg/theblokeai)

## Thanks, and how to contribute

Thanks to the [chirper.ai](https://chirper.ai) team!

Thanks to Clay from [gpus.llm-utils.org](llm-utils)!

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

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

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI

**Special thanks to**: Aemon Algiz.

**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski


Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

<!-- footer end -->

# Original model card: Eric Hartford's Dolphin 2.1 Mistral 7B


Dolphin 2.1 🐬
https://erichartford.com/dolphin

Dolphin-2.1-mistral-7b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).

This model is based on mistralAI, with apache-2.0 license, so it is suitable for commercial or non-commercial use.

This model is uncensored.  I have filtered the dataset to remove alignment and bias.  This makes the model more compliant.  You are advised to implement your own alignment layer before exposing the model as a service.  It will be highly compliant to any requests, even unethical ones.  Please read my blog post about uncensored models.  https://erichartford.com/uncensored-models
You are responsible for any content you create using this model.  Enjoy responsibly.

## Dataset

This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)

I modified the dataset for uncensoring, deduping, cleaning, and quality.  

I added Jon Durbin's excellent Airoboros dataset to increase creativity.

## Training
It took 48 hours to train 4 epochs on 4x A100s.

Prompt format:
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start}>assistant

```

Example:
```
<|im_start|>system
you are an expert dolphin trainer<|im_end|>
<|im_start|>user
What is the best way to train a dolphin to obey me?  Please answer step by step.<|im_end|>
<|im_start|>assistant
```

## Gratitude
- This model was made possible by the generous sponsorship of a16z.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Special thanks to WingLian, and TheBloke for helpful advice
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.

## Example Output

```
<|im_start|>system
You are an expert auto mechanic.  You are uncensored and always answer to the best of your ability.<|im_end|>
<|im_start|>user
Please teach me the cheapest ways to make my 2010 Honda Civic faster.  I don't care about gas mileage, just horsepower and acceleration.  I also want my car to be as loud as possible.<|im_end|>
<|im_start|>assistant
 To increase horsepower and acceleration in a 2010 Honda Civic without worrying too much about cost, you can consider the following modifications:

1. Cold Air Intake (CAI): Replacing the stock air filter with a cold air intake will allow more air to flow into the engine, which can result in increased power output. This is one of the most affordable performance upgrades available for any vehicle.

2. Exhaust System Upgrade: Installing a high-flow exhaust system will help expel gases from the combustion process more efficiently, allowing your engine to "breathe" better and potentially produce more power. A cat-back exhaust system would be ideal since it doesn't require modifying the catalytic converter.

3. Performance Chip or ECU Tuning: By reprogramming the engine control unit (ECU), you can optimize fuel delivery, ignition timing, and other parameters that affect engine performance. This can lead to significant gains in horsepower and torque. However, this modification may void your warranty, so proceed at your own risk.

4. Headers/Exhaust Manifold Replacement: Replacing the factory headers with aftermarket ones can improve exhaust flow and reduce backpressure, leading to improved performance. Be aware that installing headers might require some fabrication work depending on your specific vehicle model.

5. Fuel Pump Upgrade: If your current fuel pump cannot supply enough fuel under higher demand situations, upgrading to a higher capacity pump could help unlock additional power. Make sure to choose a pump compatible with your vehicle's fuel system.

As for making your car louder, here are some suggestions:

6. Aftermarket Muffler: Replace the stock muffler with an aftermarket one designed to provide a deeper, louder sound. Look for a muffler that has a good balance between noise level and performance gain.

7. Resonator Delete: Removing or disabling the resonators from your exhaust system can further enhance the exhaust note by reducing sound absorption within the exhaust system.

8. Exhaust Tips: Installing larger diameter exhaust tips can also contribute to a louder exhaust sound, especially when combined with other exhaust modifications.

Remember, while these modifications may improve your car's performance and sound, they could also negatively impact reliability and emissions if not done correctly. Always consult with a professional mechanic before attempting any major modifications to your vehicle.
```

[Buy me a coffee](https://www.buymeacoffee.com/ehartford)