TheBloke commited on
Commit
3a192ff
1 Parent(s): 47e9ff7

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +363 -0
README.md ADDED
@@ -0,0 +1,363 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: TencentARC/LLaMA-Pro-8B
3
+ inference: false
4
+ license: llama2
5
+ model_creator: ARC Lab, Tencent PCG
6
+ model_name: Llama Pro 8B
7
+ model_type: llama
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
+ # Llama Pro 8B - AWQ
33
+ - Model creator: [ARC Lab, Tencent PCG](https://huggingface.co/TencentARC)
34
+ - Original model: [Llama Pro 8B](https://huggingface.co/TencentARC/LLaMA-Pro-8B)
35
+
36
+ <!-- description start -->
37
+ ## Description
38
+
39
+ This repo contains AWQ model files for [ARC Lab, Tencent PCG's Llama Pro 8B](https://huggingface.co/TencentARC/LLaMA-Pro-8B).
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
+ AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
49
+
50
+ It is supported by:
51
+
52
+ - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
53
+ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
54
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
55
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
56
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
57
+
58
+ <!-- description end -->
59
+ <!-- repositories-available start -->
60
+ ## Repositories available
61
+
62
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/LLaMA-Pro-8B-AWQ)
63
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/LLaMA-Pro-8B-GPTQ)
64
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/LLaMA-Pro-8B-GGUF)
65
+ * [ARC Lab, Tencent PCG's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TencentARC/LLaMA-Pro-8B)
66
+ <!-- repositories-available end -->
67
+
68
+ <!-- prompt-template start -->
69
+ ## Prompt template: None
70
+
71
+ ```
72
+ {prompt}
73
+
74
+ ```
75
+
76
+ <!-- prompt-template end -->
77
+
78
+
79
+ <!-- README_AWQ.md-provided-files start -->
80
+ ## Provided files, and AWQ parameters
81
+
82
+ I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
83
+
84
+ Models are released as sharded safetensors files.
85
+
86
+ | Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
87
+ | ------ | ---- | -- | ----------- | ------- | ---- |
88
+ | [main](https://huggingface.co/TheBloke/LLaMA-Pro-8B-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.73 GB
89
+
90
+ <!-- README_AWQ.md-provided-files end -->
91
+
92
+ <!-- README_AWQ.md-text-generation-webui start -->
93
+ ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
94
+
95
+ Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
96
+
97
+ 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.
98
+
99
+ 1. Click the **Model tab**.
100
+ 2. Under **Download custom model or LoRA**, enter `TheBloke/LLaMA-Pro-8B-AWQ`.
101
+ 3. Click **Download**.
102
+ 4. The model will start downloading. Once it's finished it will say "Done".
103
+ 5. In the top left, click the refresh icon next to **Model**.
104
+ 6. In the **Model** dropdown, choose the model you just downloaded: `LLaMA-Pro-8B-AWQ`
105
+ 7. Select **Loader: AutoAWQ**.
106
+ 8. Click Load, and the model will load and is now ready for use.
107
+ 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.
108
+ 10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
109
+ <!-- README_AWQ.md-text-generation-webui end -->
110
+
111
+ <!-- README_AWQ.md-use-from-vllm start -->
112
+ ## Multi-user inference server: vLLM
113
+
114
+ Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
115
+
116
+ - Please ensure you are using vLLM version 0.2 or later.
117
+ - When using vLLM as a server, pass the `--quantization awq` parameter.
118
+
119
+ For example:
120
+
121
+ ```shell
122
+ python3 -m vllm.entrypoints.api_server --model TheBloke/LLaMA-Pro-8B-AWQ --quantization awq --dtype auto
123
+ ```
124
+
125
+ - When using vLLM from Python code, again set `quantization=awq`.
126
+
127
+ For example:
128
+
129
+ ```python
130
+ from vllm import LLM, SamplingParams
131
+
132
+ prompts = [
133
+ "Tell me about AI",
134
+ "Write a story about llamas",
135
+ "What is 291 - 150?",
136
+ "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
137
+ ]
138
+ prompt_template=f'''{prompt}
139
+ '''
140
+
141
+ prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
142
+
143
+ sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
144
+
145
+ llm = LLM(model="TheBloke/LLaMA-Pro-8B-AWQ", quantization="awq", dtype="auto")
146
+
147
+ outputs = llm.generate(prompts, sampling_params)
148
+
149
+ # Print the outputs.
150
+ for output in outputs:
151
+ prompt = output.prompt
152
+ generated_text = output.outputs[0].text
153
+ print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
154
+ ```
155
+ <!-- README_AWQ.md-use-from-vllm start -->
156
+
157
+ <!-- README_AWQ.md-use-from-tgi start -->
158
+ ## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
159
+
160
+ Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
161
+
162
+ Example Docker parameters:
163
+
164
+ ```shell
165
+ --model-id TheBloke/LLaMA-Pro-8B-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
166
+ ```
167
+
168
+ Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
169
+
170
+ ```shell
171
+ pip3 install huggingface-hub
172
+ ```
173
+
174
+ ```python
175
+ from huggingface_hub import InferenceClient
176
+
177
+ endpoint_url = "https://your-endpoint-url-here"
178
+
179
+ prompt = "Tell me about AI"
180
+ prompt_template=f'''{prompt}
181
+ '''
182
+
183
+ client = InferenceClient(endpoint_url)
184
+ response = client.text_generation(prompt,
185
+ max_new_tokens=128,
186
+ do_sample=True,
187
+ temperature=0.7,
188
+ top_p=0.95,
189
+ top_k=40,
190
+ repetition_penalty=1.1)
191
+
192
+ print(f"Model output: ", response)
193
+ ```
194
+ <!-- README_AWQ.md-use-from-tgi end -->
195
+
196
+ <!-- README_AWQ.md-use-from-python start -->
197
+ ## Inference from Python code using Transformers
198
+
199
+ ### Install the necessary packages
200
+
201
+ - Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
202
+ - Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
203
+
204
+ ```shell
205
+ pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
206
+ ```
207
+
208
+ Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
209
+
210
+ If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
211
+
212
+ ```shell
213
+ pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
214
+ ```
215
+
216
+ If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
217
+
218
+ ```shell
219
+ pip3 uninstall -y autoawq
220
+ git clone https://github.com/casper-hansen/AutoAWQ
221
+ cd AutoAWQ
222
+ pip3 install .
223
+ ```
224
+
225
+ ### Transformers example code (requires Transformers 4.35.0 and later)
226
+
227
+ ```python
228
+ from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
229
+
230
+ model_name_or_path = "TheBloke/LLaMA-Pro-8B-AWQ"
231
+
232
+ tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
233
+ model = AutoModelForCausalLM.from_pretrained(
234
+ model_name_or_path,
235
+ low_cpu_mem_usage=True,
236
+ device_map="cuda:0"
237
+ )
238
+
239
+ # Using the text streamer to stream output one token at a time
240
+ streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
241
+
242
+ prompt = "Tell me about AI"
243
+ prompt_template=f'''{prompt}
244
+ '''
245
+
246
+ # Convert prompt to tokens
247
+ tokens = tokenizer(
248
+ prompt_template,
249
+ return_tensors='pt'
250
+ ).input_ids.cuda()
251
+
252
+ generation_params = {
253
+ "do_sample": True,
254
+ "temperature": 0.7,
255
+ "top_p": 0.95,
256
+ "top_k": 40,
257
+ "max_new_tokens": 512,
258
+ "repetition_penalty": 1.1
259
+ }
260
+
261
+ # Generate streamed output, visible one token at a time
262
+ generation_output = model.generate(
263
+ tokens,
264
+ streamer=streamer,
265
+ **generation_params
266
+ )
267
+
268
+ # Generation without a streamer, which will include the prompt in the output
269
+ generation_output = model.generate(
270
+ tokens,
271
+ **generation_params
272
+ )
273
+
274
+ # Get the tokens from the output, decode them, print them
275
+ token_output = generation_output[0]
276
+ text_output = tokenizer.decode(token_output)
277
+ print("model.generate output: ", text_output)
278
+
279
+ # Inference is also possible via Transformers' pipeline
280
+ from transformers import pipeline
281
+
282
+ pipe = pipeline(
283
+ "text-generation",
284
+ model=model,
285
+ tokenizer=tokenizer,
286
+ **generation_params
287
+ )
288
+
289
+ pipe_output = pipe(prompt_template)[0]['generated_text']
290
+ print("pipeline output: ", pipe_output)
291
+
292
+ ```
293
+ <!-- README_AWQ.md-use-from-python end -->
294
+
295
+ <!-- README_AWQ.md-compatibility start -->
296
+ ## Compatibility
297
+
298
+ The files provided are tested to work with:
299
+
300
+ - [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
301
+ - [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
302
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
303
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
304
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
305
+
306
+ <!-- README_AWQ.md-compatibility end -->
307
+
308
+ <!-- footer start -->
309
+ <!-- 200823 -->
310
+ ## Discord
311
+
312
+ For further support, and discussions on these models and AI in general, join us at:
313
+
314
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
315
+
316
+ ## Thanks, and how to contribute
317
+
318
+ Thanks to the [chirper.ai](https://chirper.ai) team!
319
+
320
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
321
+
322
+ 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.
323
+
324
+ 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.
325
+
326
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
327
+
328
+ * Patreon: https://patreon.com/TheBlokeAI
329
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
330
+
331
+ **Special thanks to**: Aemon Algiz.
332
+
333
+ **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
334
+
335
+
336
+ Thank you to all my generous patrons and donaters!
337
+
338
+ And thank you again to a16z for their generous grant.
339
+
340
+ <!-- footer end -->
341
+
342
+ # Original model card: ARC Lab, Tencent PCG's Llama Pro 8B
343
+
344
+
345
+ # LLaMA-Pro-8B Model Card
346
+
347
+ ## Model Description
348
+ LLaMA-Pro is a progressive version of the original LLaMA model, enhanced by the addition of Transformer blocks. It specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
349
+
350
+ ## Development and Training
351
+ Developed by Tencent's ARC Lab, LLaMA-Pro is an 8.3 billion parameter model. It's an expansion of LLaMA2-7B, further trained on code and math corpora totaling 80 billion tokens.
352
+
353
+ ## Intended Use
354
+ This model is designed for a wide range of NLP tasks, with a focus on programming, mathematics, and general language tasks. It suits scenarios requiring integration of natural and programming languages.
355
+
356
+ ## Performance
357
+ LLaMA-Pro demonstrates advanced performance across various benchmarks. It outperforms existing models in the LLaMA series in handling diverse tasks, showcasing its capability as an intelligent language agent.
358
+
359
+ ## Limitations
360
+ While LLaMA-Pro addresses some limitations of previous models in the series, it may still encounter challenges specific to highly specialized domains or tasks.
361
+
362
+ ## Ethical Considerations
363
+ Users should be aware of potential biases in the model and use it responsibly, considering its impact on various applications.