TheBloke commited on
Commit
84714db
1 Parent(s): 440ca1e

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -52
README.md CHANGED
@@ -2,7 +2,7 @@
2
  inference: false
3
  language:
4
  - en
5
- license: other
6
  model_creator: Gryphe
7
  model_link: https://huggingface.co/Gryphe/MythoLogic-L2-13b
8
  model_name: Mythologic L2 13B
@@ -31,18 +31,24 @@ quantized_by: TheBloke
31
  - Model creator: [Gryphe](https://huggingface.co/Gryphe)
32
  - Original model: [Mythologic L2 13B](https://huggingface.co/Gryphe/MythoLogic-L2-13b)
33
 
 
34
  ## Description
35
 
36
  This repo contains GPTQ model files for [Gryphe's Mythologic L2 13B](https://huggingface.co/Gryphe/MythoLogic-L2-13b).
37
 
38
  Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
39
 
 
 
40
  ## Repositories available
41
 
42
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ)
43
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GGML)
 
44
  * [Gryphe's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Gryphe/MythoLogic-L2-13b)
 
45
 
 
46
  ## Prompt template: Alpaca
47
 
48
  ```
@@ -52,22 +58,26 @@ Below is an instruction that describes a task. Write a response that appropriate
52
  {prompt}
53
 
54
  ### Response:
 
55
  ```
56
 
 
 
 
57
  ## Provided files and GPTQ parameters
58
 
59
  Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
60
 
61
  Each separate quant is in a different branch. See below for instructions on fetching from different branches.
62
 
63
- All GPTQ files are made with AutoGPTQ.
64
 
65
  <details>
66
  <summary>Explanation of GPTQ parameters</summary>
67
 
68
  - Bits: The bit size of the quantised model.
69
  - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
70
- - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have issues with models that use Act Order plus Group Size.
71
  - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
72
  - GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
73
  - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
@@ -77,15 +87,18 @@ All GPTQ files are made with AutoGPTQ.
77
 
78
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
79
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
80
- | [main](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
81
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
82
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
83
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
84
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
85
- | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
86
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
87
- | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
88
-
 
 
 
89
  ## How to download from branches
90
 
91
  - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/MythoLogic-L2-13B-GPTQ:gptq-4bit-32g-actorder_True`
@@ -94,73 +107,72 @@ All GPTQ files are made with AutoGPTQ.
94
  git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ
95
  ```
96
  - In Python Transformers code, the branch is the `revision` parameter; see below.
97
-
 
98
  ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
99
 
100
  Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
101
 
102
- It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
103
 
104
  1. Click the **Model tab**.
105
  2. Under **Download custom model or LoRA**, enter `TheBloke/MythoLogic-L2-13B-GPTQ`.
106
  - To download from a specific branch, enter for example `TheBloke/MythoLogic-L2-13B-GPTQ:gptq-4bit-32g-actorder_True`
107
  - see Provided Files above for the list of branches for each option.
108
  3. Click **Download**.
109
- 4. The model will start downloading. Once it's finished it will say "Done"
110
  5. In the top left, click the refresh icon next to **Model**.
111
  6. In the **Model** dropdown, choose the model you just downloaded: `MythoLogic-L2-13B-GPTQ`
112
  7. The model will automatically load, and is now ready for use!
113
  8. 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.
114
- * Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
115
  9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
 
116
 
 
117
  ## How to use this GPTQ model from Python code
118
 
119
- First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) 0.3.1 or later installed:
120
 
121
- ```
122
- pip3 install auto-gptq
123
- ```
124
 
125
- If you have problems installing AutoGPTQ, please build from source instead:
 
 
126
  ```
 
 
 
 
127
  pip3 uninstall -y auto-gptq
128
  git clone https://github.com/PanQiWei/AutoGPTQ
129
  cd AutoGPTQ
130
  pip3 install .
131
  ```
132
 
133
- Then try the following example code:
 
 
 
 
 
 
 
 
134
 
135
  ```python
136
- from transformers import AutoTokenizer, pipeline, logging
137
- from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
138
 
139
  model_name_or_path = "TheBloke/MythoLogic-L2-13B-GPTQ"
140
-
141
- use_triton = False
 
 
 
 
142
 
143
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
144
 
145
- model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
146
- use_safetensors=True,
147
- trust_remote_code=False,
148
- device="cuda:0",
149
- use_triton=use_triton,
150
- quantize_config=None)
151
-
152
- """
153
- # To download from a specific branch, use the revision parameter, as in this example:
154
- # Note that `revision` requires AutoGPTQ 0.3.1 or later!
155
-
156
- model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
157
- revision="gptq-4bit-32g-actorder_True",
158
- use_safetensors=True,
159
- trust_remote_code=False,
160
- device="cuda:0",
161
- quantize_config=None)
162
- """
163
-
164
  prompt = "Tell me about AI"
165
  prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
166
 
@@ -168,6 +180,7 @@ prompt_template=f'''Below is an instruction that describes a task. Write a respo
168
  {prompt}
169
 
170
  ### Response:
 
171
  '''
172
 
173
  print("\n\n*** Generate:")
@@ -178,9 +191,6 @@ print(tokenizer.decode(output[0]))
178
 
179
  # Inference can also be done using transformers' pipeline
180
 
181
- # Prevent printing spurious transformers error when using pipeline with AutoGPTQ
182
- logging.set_verbosity(logging.CRITICAL)
183
-
184
  print("*** Pipeline:")
185
  pipe = pipeline(
186
  "text-generation",
@@ -194,12 +204,17 @@ pipe = pipeline(
194
 
195
  print(pipe(prompt_template)[0]['generated_text'])
196
  ```
 
197
 
 
198
  ## Compatibility
199
 
200
- The files provided will work with AutoGPTQ (CUDA and Triton modes), GPTQ-for-LLaMa (only CUDA has been tested), and Occ4m's GPTQ-for-LLaMa fork.
 
 
201
 
202
- ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
203
 
204
  <!-- footer start -->
205
  <!-- 200823 -->
@@ -224,7 +239,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
224
 
225
  **Special thanks to**: Aemon Algiz.
226
 
227
- **Patreon special mentions**: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
228
 
229
 
230
  Thank you to all my generous patrons and donaters!
 
2
  inference: false
3
  language:
4
  - en
5
+ license: llama2
6
  model_creator: Gryphe
7
  model_link: https://huggingface.co/Gryphe/MythoLogic-L2-13b
8
  model_name: Mythologic L2 13B
 
31
  - Model creator: [Gryphe](https://huggingface.co/Gryphe)
32
  - Original model: [Mythologic L2 13B](https://huggingface.co/Gryphe/MythoLogic-L2-13b)
33
 
34
+ <!-- description start -->
35
  ## Description
36
 
37
  This repo contains GPTQ model files for [Gryphe's Mythologic L2 13B](https://huggingface.co/Gryphe/MythoLogic-L2-13b).
38
 
39
  Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
40
 
41
+ <!-- description end -->
42
+ <!-- repositories-available start -->
43
  ## Repositories available
44
 
45
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ)
46
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GGUF)
47
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GGML)
48
  * [Gryphe's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Gryphe/MythoLogic-L2-13b)
49
+ <!-- repositories-available end -->
50
 
51
+ <!-- prompt-template start -->
52
  ## Prompt template: Alpaca
53
 
54
  ```
 
58
  {prompt}
59
 
60
  ### Response:
61
+
62
  ```
63
 
64
+ <!-- prompt-template end -->
65
+
66
+ <!-- README_GPTQ.md-provided-files start -->
67
  ## Provided files and GPTQ parameters
68
 
69
  Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
70
 
71
  Each separate quant is in a different branch. See below for instructions on fetching from different branches.
72
 
73
+ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
74
 
75
  <details>
76
  <summary>Explanation of GPTQ parameters</summary>
77
 
78
  - Bits: The bit size of the quantised model.
79
  - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
80
+ - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
81
  - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
82
  - GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
83
  - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
 
87
 
88
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
89
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
90
+ | [main](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
91
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
92
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
93
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
94
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
95
+ | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
96
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
97
+ | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
98
+
99
+ <!-- README_GPTQ.md-provided-files end -->
100
+
101
+ <!-- README_GPTQ.md-download-from-branches start -->
102
  ## How to download from branches
103
 
104
  - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/MythoLogic-L2-13B-GPTQ:gptq-4bit-32g-actorder_True`
 
107
  git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/MythoLogic-L2-13B-GPTQ
108
  ```
109
  - In Python Transformers code, the branch is the `revision` parameter; see below.
110
+ <!-- README_GPTQ.md-download-from-branches end -->
111
+ <!-- README_GPTQ.md-text-generation-webui start -->
112
  ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
113
 
114
  Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
115
 
116
+ 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.
117
 
118
  1. Click the **Model tab**.
119
  2. Under **Download custom model or LoRA**, enter `TheBloke/MythoLogic-L2-13B-GPTQ`.
120
  - To download from a specific branch, enter for example `TheBloke/MythoLogic-L2-13B-GPTQ:gptq-4bit-32g-actorder_True`
121
  - see Provided Files above for the list of branches for each option.
122
  3. Click **Download**.
123
+ 4. The model will start downloading. Once it's finished it will say "Done".
124
  5. In the top left, click the refresh icon next to **Model**.
125
  6. In the **Model** dropdown, choose the model you just downloaded: `MythoLogic-L2-13B-GPTQ`
126
  7. The model will automatically load, and is now ready for use!
127
  8. 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.
128
+ * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
129
  9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
130
+ <!-- README_GPTQ.md-text-generation-webui end -->
131
 
132
+ <!-- README_GPTQ.md-use-from-python start -->
133
  ## How to use this GPTQ model from Python code
134
 
135
+ ### Install the necessary packages
136
 
137
+ Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
 
 
138
 
139
+ ```shell
140
+ pip3 install transformers>=4.32.0 optimum>=1.12.0
141
+ pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
142
  ```
143
+
144
+ If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
145
+
146
+ ```shell
147
  pip3 uninstall -y auto-gptq
148
  git clone https://github.com/PanQiWei/AutoGPTQ
149
  cd AutoGPTQ
150
  pip3 install .
151
  ```
152
 
153
+ ### For CodeLlama models only: you must use Transformers 4.33.0 or later.
154
+
155
+ If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
156
+ ```shell
157
+ pip3 uninstall -y transformers
158
+ pip3 install git+https://github.com/huggingface/transformers.git
159
+ ```
160
+
161
+ ### You can then use the following code
162
 
163
  ```python
164
+ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
165
 
166
  model_name_or_path = "TheBloke/MythoLogic-L2-13B-GPTQ"
167
+ # To use a different branch, change revision
168
+ # For example: revision="gptq-4bit-32g-actorder_True"
169
+ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
170
+ torch_dtype=torch.float16,
171
+ device_map="auto",
172
+ revision="main")
173
 
174
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
175
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
176
  prompt = "Tell me about AI"
177
  prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
178
 
 
180
  {prompt}
181
 
182
  ### Response:
183
+
184
  '''
185
 
186
  print("\n\n*** Generate:")
 
191
 
192
  # Inference can also be done using transformers' pipeline
193
 
 
 
 
194
  print("*** Pipeline:")
195
  pipe = pipeline(
196
  "text-generation",
 
204
 
205
  print(pipe(prompt_template)[0]['generated_text'])
206
  ```
207
+ <!-- README_GPTQ.md-use-from-python end -->
208
 
209
+ <!-- README_GPTQ.md-compatibility start -->
210
  ## Compatibility
211
 
212
+ The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
213
+
214
+ [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
215
 
216
+ [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
217
+ <!-- README_GPTQ.md-compatibility end -->
218
 
219
  <!-- footer start -->
220
  <!-- 200823 -->
 
239
 
240
  **Special thanks to**: Aemon Algiz.
241
 
242
+ **Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
243
 
244
 
245
  Thank you to all my generous patrons and donaters!