TheBloke commited on
Commit
48063d0
1 Parent(s): 8e42e03

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +116 -62
README.md CHANGED
@@ -1,7 +1,16 @@
1
  ---
 
2
  inference: false
3
  license: other
 
 
4
  model_type: llama
 
 
 
 
 
 
5
  ---
6
 
7
  <!-- header start -->
@@ -21,146 +30,189 @@ model_type: llama
21
  <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
22
  <!-- header end -->
23
 
24
- # Tim Dettmers' Guanaco 33B GPTQ
 
 
25
 
26
- These files are GPTQ model files for [Tim Dettmers' Guanaco 33B](https://huggingface.co/timdettmers/guanaco-33b-merged).
 
27
 
28
- 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.
29
 
30
- These models were quantised using hardware kindly provided by [Latitude.sh](https://www.latitude.sh/accelerate).
31
 
 
 
32
  ## Repositories available
33
 
 
34
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/guanaco-33B-GPTQ)
35
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/guanaco-33B-GGML)
36
- * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/timdettmers/guanaco-33b-merged)
 
37
 
 
38
  ## Prompt template: Guanaco
39
 
40
  ```
41
  ### Human: {prompt}
42
  ### Assistant:
 
43
  ```
44
 
45
- ## Provided files
 
 
 
 
46
 
47
  Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
48
 
49
  Each separate quant is in a different branch. See below for instructions on fetching from different branches.
50
 
51
- | Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
52
- | ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
53
- | main | 4 | None | True | 16.94 GB | True | GPTQ-for-LLaMa | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
54
- | gptq-4bit-32g-actorder_True | 4 | 32 | True | 19.44 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 32g gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
55
- | gptq-4bit-64g-actorder_True | 4 | 64 | True | 18.18 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 64g uses less VRAM than 32g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
56
- | gptq-4bit-128g-actorder_True | 4 | 128 | True | 17.55 GB | True | AutoGPTQ | 4-bit, with Act Order and group size. 128g uses even less VRAM, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
57
- | gptq-8bit--1g-actorder_True | 8 | None | True | 32.99 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
58
- | gptq-8bit-128g-actorder_False | 8 | 128 | False | 33.73 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
59
- | gptq-3bit--1g-actorder_True | 3 | None | True | 12.92 GB | False | AutoGPTQ | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
60
- | gptq-3bit-128g-actorder_False | 3 | 128 | False | 13.51 GB | False | AutoGPTQ | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
61
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  ## How to download from branches
63
 
64
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/guanaco-33B-GPTQ:gptq-4bit-32g-actorder_True`
65
  - With Git, you can clone a branch with:
66
  ```
67
- git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/guanaco-33B-GPTQ`
68
  ```
69
  - In Python Transformers code, the branch is the `revision` parameter; see below.
70
-
 
71
  ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
72
 
73
  Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
74
 
75
- It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
76
 
77
  1. Click the **Model tab**.
78
  2. Under **Download custom model or LoRA**, enter `TheBloke/guanaco-33B-GPTQ`.
79
- - To download from a specific branch, enter for example `TheBloke/guanaco-33B-GPTQ:gptq-4bit-32g-actorder_True`
80
  - see Provided Files above for the list of branches for each option.
81
  3. Click **Download**.
82
- 4. The model will start downloading. Once it's finished it will say "Done"
83
  5. In the top left, click the refresh icon next to **Model**.
84
  6. In the **Model** dropdown, choose the model you just downloaded: `guanaco-33B-GPTQ`
85
  7. The model will automatically load, and is now ready for use!
86
  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.
87
- * Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
88
  9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
 
89
 
 
90
  ## How to use this GPTQ model from Python code
91
 
92
- First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
93
 
94
- `GITHUB_ACTIONS=true pip install auto-gptq`
95
 
96
- Then try the following example code:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
 
98
  ```python
99
- from transformers import AutoTokenizer, pipeline, logging
100
- from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
101
 
102
  model_name_or_path = "TheBloke/guanaco-33B-GPTQ"
103
- model_basename = "guanaco-33b-GPTQ-4bit--1g.act.order"
104
-
105
- use_triton = False
 
 
 
106
 
107
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
108
 
109
- model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
110
- model_basename=model_basename
111
- use_safetensors=True,
112
- trust_remote_code=False,
113
- device="cuda:0",
114
- use_triton=use_triton,
115
- quantize_config=None)
116
-
117
- """
118
- To download from a specific branch, use the revision parameter, as in this example:
119
-
120
- model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
121
- revision="gptq-4bit-32g-actorder_True",
122
- model_basename=model_basename,
123
- use_safetensors=True,
124
- trust_remote_code=False,
125
- device="cuda:0",
126
- quantize_config=None)
127
- """
128
-
129
  prompt = "Tell me about AI"
130
  prompt_template=f'''### Human: {prompt}
131
  ### Assistant:
 
132
  '''
133
 
134
  print("\n\n*** Generate:")
135
 
136
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
137
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
138
  print(tokenizer.decode(output[0]))
139
 
140
  # Inference can also be done using transformers' pipeline
141
 
142
- # Prevent printing spurious transformers error when using pipeline with AutoGPTQ
143
- logging.set_verbosity(logging.CRITICAL)
144
-
145
  print("*** Pipeline:")
146
  pipe = pipeline(
147
  "text-generation",
148
  model=model,
149
  tokenizer=tokenizer,
150
  max_new_tokens=512,
 
151
  temperature=0.7,
152
  top_p=0.95,
153
- repetition_penalty=1.15
 
154
  )
155
 
156
  print(pipe(prompt_template)[0]['generated_text'])
157
  ```
 
158
 
 
159
  ## Compatibility
160
 
161
- 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.
 
 
162
 
163
- ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
164
 
165
  <!-- footer start -->
166
  <!-- 200823 -->
@@ -170,10 +222,12 @@ For further support, and discussions on these models and AI in general, join us
170
 
171
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
172
 
173
- ## Thanks, and how to contribute.
174
 
175
  Thanks to the [chirper.ai](https://chirper.ai) team!
176
 
 
 
177
  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.
178
 
179
  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.
@@ -185,7 +239,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
185
 
186
  **Special thanks to**: Aemon Algiz.
187
 
188
- **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
189
 
190
 
191
  Thank you to all my generous patrons and donaters!
@@ -196,4 +250,4 @@ And thank you again to a16z for their generous grant.
196
 
197
  # Original model card: Tim Dettmers' Guanaco 33B
198
 
199
- No original model card was provided.
 
1
  ---
2
+ base_model: https://huggingface.co/timdettmers/guanaco-33b-merged
3
  inference: false
4
  license: other
5
+ model_creator: Tim Dettmers
6
+ model_name: Guanaco 33B
7
  model_type: llama
8
+ prompt_template: '### Human: {prompt}
9
+
10
+ ### Assistant:
11
+
12
+ '
13
+ quantized_by: TheBloke
14
  ---
15
 
16
  <!-- header start -->
 
30
  <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
31
  <!-- header end -->
32
 
33
+ # Guanaco 33B - GPTQ
34
+ - Model creator: [Tim Dettmers](https://huggingface.co/timdettmers)
35
+ - Original model: [Guanaco 33B](https://huggingface.co/timdettmers/guanaco-33b-merged)
36
 
37
+ <!-- description start -->
38
+ ## Description
39
 
40
+ This repo contains GPTQ model files for [Tim Dettmers' Guanaco 33B](https://huggingface.co/timdettmers/guanaco-33b-merged).
41
 
42
+ 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.
43
 
44
+ <!-- description end -->
45
+ <!-- repositories-available start -->
46
  ## Repositories available
47
 
48
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/guanaco-33B-AWQ)
49
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/guanaco-33B-GPTQ)
50
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/guanaco-33B-GGUF)
51
+ * [Tim Dettmers's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/timdettmers/guanaco-33b-merged)
52
+ <!-- repositories-available end -->
53
 
54
+ <!-- prompt-template start -->
55
  ## Prompt template: Guanaco
56
 
57
  ```
58
  ### Human: {prompt}
59
  ### Assistant:
60
+
61
  ```
62
 
63
+ <!-- prompt-template end -->
64
+
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.
84
+ - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
85
+
86
+ </details>
87
+
88
+ | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
89
+ | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
90
+ | [main](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/main) | 4 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 16.94 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
91
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 19.44 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
92
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 18.18 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
93
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 17.55 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
94
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 32.99 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
95
+ | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 33.73 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
96
+ | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 12.92 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
97
+ | [gptq-3bit-128g-actorder_False](https://huggingface.co/TheBloke/guanaco-33B-GPTQ/tree/gptq-3bit-128g-actorder_False) | 3 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.51 GB | No | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
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/guanaco-33B-GPTQ:main`
105
  - With Git, you can clone a branch with:
106
  ```
107
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/guanaco-33B-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/guanaco-33B-GPTQ`.
120
+ - To download from a specific branch, enter for example `TheBloke/guanaco-33B-GPTQ:main`
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: `guanaco-33B-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/guanaco-33B-GPTQ"
167
+ # To use a different branch, change revision
168
+ # For example: revision="main"
169
+ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
170
+ device_map="auto",
171
+ trust_remote_code=False,
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'''### Human: {prompt}
178
  ### Assistant:
179
+
180
  '''
181
 
182
  print("\n\n*** Generate:")
183
 
184
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
185
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
186
  print(tokenizer.decode(output[0]))
187
 
188
  # Inference can also be done using transformers' pipeline
189
 
 
 
 
190
  print("*** Pipeline:")
191
  pipe = pipeline(
192
  "text-generation",
193
  model=model,
194
  tokenizer=tokenizer,
195
  max_new_tokens=512,
196
+ do_sample=True,
197
  temperature=0.7,
198
  top_p=0.95,
199
+ top_k=40,
200
+ repetition_penalty=1.1
201
  )
202
 
203
  print(pipe(prompt_template)[0]['generated_text'])
204
  ```
205
+ <!-- README_GPTQ.md-use-from-python end -->
206
 
207
+ <!-- README_GPTQ.md-compatibility start -->
208
  ## Compatibility
209
 
210
+ 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).
211
+
212
+ [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.
213
 
214
+ [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
215
+ <!-- README_GPTQ.md-compatibility end -->
216
 
217
  <!-- footer start -->
218
  <!-- 200823 -->
 
222
 
223
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
224
 
225
+ ## Thanks, and how to contribute
226
 
227
  Thanks to the [chirper.ai](https://chirper.ai) team!
228
 
229
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
230
+
231
  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.
232
 
233
  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.
 
239
 
240
  **Special thanks to**: Aemon Algiz.
241
 
242
+ **Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
243
 
244
 
245
  Thank you to all my generous patrons and donaters!
 
250
 
251
  # Original model card: Tim Dettmers' Guanaco 33B
252
 
253
+ No original model card was available.