TheBloke commited on
Commit
641688c
1 Parent(s): a577df4

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +95 -57
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  inference: false
3
- license: other
4
  model_creator: totally-not-an-llm
5
  model_link: https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b
6
  model_name: AlpacaCielo 13B
@@ -29,112 +29,148 @@ quantized_by: TheBloke
29
  - Model creator: [totally-not-an-llm](https://huggingface.co/totally-not-an-llm)
30
  - Original model: [AlpacaCielo 13B](https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b)
31
 
 
32
  ## Description
33
 
34
  This repo contains GPTQ model files for [totally-not-an-llm's AlpacaCielo 13B](https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b).
35
 
36
  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.
37
 
 
 
38
  ## Repositories available
39
 
40
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ)
41
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGML)
 
42
  * [totally-not-an-llm's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b)
 
43
 
 
44
  ## Prompt template: Guanaco
45
 
46
  ```
47
  ### Human: {prompt}
48
  ### Assistant:
 
49
  ```
50
 
51
- ## Provided files
 
 
 
52
 
53
  Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
54
 
55
  Each separate quant is in a different branch. See below for instructions on fetching from different branches.
56
 
57
- | Branch | Bits | Group Size | Act Order (desc_act) | File Size | ExLlama Compatible? | Made With | Description |
58
- | ------ | ---- | ---------- | -------------------- | --------- | ------------------- | --------- | ----------- |
59
- | main | 4 | 128 | False | 7.26 GB | True | AutoGPTQ | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
60
- | gptq-4bit-32g-actorder_True | 4 | 32 | True | 8.00 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. |
61
- | gptq-4bit-64g-actorder_True | 4 | 64 | True | 7.51 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. |
62
- | gptq-4bit-128g-actorder_True | 4 | 128 | True | 7.26 GB | True | AutoGPTQ | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. Poor AutoGPTQ CUDA speed. |
63
- | gptq-8bit--1g-actorder_True | 8 | None | True | 13.36 GB | False | AutoGPTQ | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
64
- | gptq-8bit-128g-actorder_False | 8 | 128 | False | 13.65 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
65
- | gptq-8bit-128g-actorder_True | 8 | 128 | True | 13.65 GB | False | AutoGPTQ | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
66
- | gptq-8bit-64g-actorder_True | 8 | 64 | True | 13.95 GB | False | AutoGPTQ | 8-bit, with group size 64g and Act Order for maximum inference quality. Poor AutoGPTQ CUDA speed. |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
 
 
 
68
  ## How to download from branches
69
 
70
  - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/AlpacaCielo-13B-GPTQ:gptq-4bit-32g-actorder_True`
71
  - With Git, you can clone a branch with:
72
  ```
73
- git clone --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ`
74
  ```
75
  - In Python Transformers code, the branch is the `revision` parameter; see below.
76
-
 
77
  ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
78
 
79
  Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
80
 
81
- It is strongly recommended to use the text-generation-webui one-click-installers unless you know how to make a manual install.
82
 
83
  1. Click the **Model tab**.
84
  2. Under **Download custom model or LoRA**, enter `TheBloke/AlpacaCielo-13B-GPTQ`.
85
  - To download from a specific branch, enter for example `TheBloke/AlpacaCielo-13B-GPTQ:gptq-4bit-32g-actorder_True`
86
  - see Provided Files above for the list of branches for each option.
87
  3. Click **Download**.
88
- 4. The model will start downloading. Once it's finished it will say "Done"
89
  5. In the top left, click the refresh icon next to **Model**.
90
  6. In the **Model** dropdown, choose the model you just downloaded: `AlpacaCielo-13B-GPTQ`
91
  7. The model will automatically load, and is now ready for use!
92
  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.
93
- * Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
94
  9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
 
95
 
 
96
  ## How to use this GPTQ model from Python code
97
 
98
- First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
 
 
99
 
100
- `GITHUB_ACTIONS=true pip install auto-gptq`
 
 
 
 
 
101
 
102
- Then try the following example code:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
 
104
  ```python
105
- from transformers import AutoTokenizer, pipeline, logging
106
- from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
107
 
108
  model_name_or_path = "TheBloke/AlpacaCielo-13B-GPTQ"
109
- model_basename = "model"
110
-
111
- use_triton = False
 
 
 
112
 
113
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
114
 
115
- model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
116
- model_basename=model_basename,
117
- use_safetensors=True,
118
- trust_remote_code=False,
119
- device="cuda:0",
120
- use_triton=use_triton,
121
- quantize_config=None)
122
-
123
- """
124
- To download from a specific branch, use the revision parameter, as in this example:
125
-
126
- model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
127
- revision="gptq-4bit-32g-actorder_True",
128
- model_basename=model_basename,
129
- use_safetensors=True,
130
- trust_remote_code=False,
131
- device="cuda:0",
132
- quantize_config=None)
133
- """
134
-
135
  prompt = "Tell me about AI"
136
  prompt_template=f'''### Human: {prompt}
137
  ### Assistant:
 
138
  '''
139
 
140
  print("\n\n*** Generate:")
@@ -145,9 +181,6 @@ print(tokenizer.decode(output[0]))
145
 
146
  # Inference can also be done using transformers' pipeline
147
 
148
- # Prevent printing spurious transformers error when using pipeline with AutoGPTQ
149
- logging.set_verbosity(logging.CRITICAL)
150
-
151
  print("*** Pipeline:")
152
  pipe = pipeline(
153
  "text-generation",
@@ -161,12 +194,17 @@ pipe = pipeline(
161
 
162
  print(pipe(prompt_template)[0]['generated_text'])
163
  ```
 
164
 
 
165
  ## Compatibility
166
 
167
- 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.
 
 
168
 
169
- ExLlama works with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
 
170
 
171
  <!-- footer start -->
172
  <!-- 200823 -->
@@ -191,7 +229,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
191
 
192
  **Special thanks to**: Aemon Algiz.
193
 
194
- **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
195
 
196
 
197
  Thank you to all my generous patrons and donaters!
@@ -210,13 +248,13 @@ And thank you again to a16z for their generous grant.
210
  <figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
211
  </figure>
212
 
213
- ***
214
- Disclaimer: The model might have a tokenizer issue, but functions. Updates to come.
215
- ***
216
-
217
  AlpacaCielo-13b is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes. It is a triple model merge of Nous-Hermes + Guanaco + Storywriter. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
218
 
219
- **Prompt format is:**
 
 
 
 
220
 
221
  ```
222
  ### Human: {prompt}
 
1
  ---
2
  inference: false
3
+ license: llama2
4
  model_creator: totally-not-an-llm
5
  model_link: https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b
6
  model_name: AlpacaCielo 13B
 
29
  - Model creator: [totally-not-an-llm](https://huggingface.co/totally-not-an-llm)
30
  - Original model: [AlpacaCielo 13B](https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b)
31
 
32
+ <!-- description start -->
33
  ## Description
34
 
35
  This repo contains GPTQ model files for [totally-not-an-llm's AlpacaCielo 13B](https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b).
36
 
37
  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.
38
 
39
+ <!-- description end -->
40
+ <!-- repositories-available start -->
41
  ## Repositories available
42
 
43
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ)
44
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGUF)
45
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGML)
46
  * [totally-not-an-llm's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/totally-not-an-llm/AlpacaCielo-13b)
47
+ <!-- repositories-available end -->
48
 
49
+ <!-- prompt-template start -->
50
  ## Prompt template: Guanaco
51
 
52
  ```
53
  ### Human: {prompt}
54
  ### Assistant:
55
+
56
  ```
57
 
58
+ <!-- prompt-template end -->
59
+
60
+ <!-- README_GPTQ.md-provided-files start -->
61
+ ## Provided files and GPTQ parameters
62
 
63
  Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
64
 
65
  Each separate quant is in a different branch. See below for instructions on fetching from different branches.
66
 
67
+ 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.
68
+
69
+ <details>
70
+ <summary>Explanation of GPTQ parameters</summary>
71
+
72
+ - Bits: The bit size of the quantised model.
73
+ - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
74
+ - 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.
75
+ - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
76
+ - 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).
77
+ - 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.
78
+ - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
79
+
80
+ </details>
81
+
82
+ | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
83
+ | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
84
+ | [main](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.26 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
85
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 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. |
86
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 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. |
87
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 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. |
88
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
89
+ | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
90
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 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. |
91
+ | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
92
 
93
+ <!-- README_GPTQ.md-provided-files end -->
94
+
95
+ <!-- README_GPTQ.md-download-from-branches start -->
96
  ## How to download from branches
97
 
98
  - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/AlpacaCielo-13B-GPTQ:gptq-4bit-32g-actorder_True`
99
  - With Git, you can clone a branch with:
100
  ```
101
+ git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ
102
  ```
103
  - In Python Transformers code, the branch is the `revision` parameter; see below.
104
+ <!-- README_GPTQ.md-download-from-branches end -->
105
+ <!-- README_GPTQ.md-text-generation-webui start -->
106
  ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
107
 
108
  Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
109
 
110
+ 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.
111
 
112
  1. Click the **Model tab**.
113
  2. Under **Download custom model or LoRA**, enter `TheBloke/AlpacaCielo-13B-GPTQ`.
114
  - To download from a specific branch, enter for example `TheBloke/AlpacaCielo-13B-GPTQ:gptq-4bit-32g-actorder_True`
115
  - see Provided Files above for the list of branches for each option.
116
  3. Click **Download**.
117
+ 4. The model will start downloading. Once it's finished it will say "Done".
118
  5. In the top left, click the refresh icon next to **Model**.
119
  6. In the **Model** dropdown, choose the model you just downloaded: `AlpacaCielo-13B-GPTQ`
120
  7. The model will automatically load, and is now ready for use!
121
  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.
122
+ * 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`.
123
  9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
124
+ <!-- README_GPTQ.md-text-generation-webui end -->
125
 
126
+ <!-- README_GPTQ.md-use-from-python start -->
127
  ## How to use this GPTQ model from Python code
128
 
129
+ ### Install the necessary packages
130
+
131
+ Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
132
 
133
+ ```shell
134
+ pip3 install transformers>=4.32.0 optimum>=1.12.0
135
+ pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
136
+ ```
137
+
138
+ If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
139
 
140
+ ```shell
141
+ pip3 uninstall -y auto-gptq
142
+ git clone https://github.com/PanQiWei/AutoGPTQ
143
+ cd AutoGPTQ
144
+ pip3 install .
145
+ ```
146
+
147
+ ### For CodeLlama models only: you must use Transformers 4.33.0 or later.
148
+
149
+ If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
150
+ ```shell
151
+ pip3 uninstall -y transformers
152
+ pip3 install git+https://github.com/huggingface/transformers.git
153
+ ```
154
+
155
+ ### You can then use the following code
156
 
157
  ```python
158
+ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
159
 
160
  model_name_or_path = "TheBloke/AlpacaCielo-13B-GPTQ"
161
+ # To use a different branch, change revision
162
+ # For example: revision="gptq-4bit-32g-actorder_True"
163
+ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
164
+ torch_dtype=torch.float16,
165
+ device_map="auto",
166
+ revision="main")
167
 
168
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
169
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
170
  prompt = "Tell me about AI"
171
  prompt_template=f'''### Human: {prompt}
172
  ### Assistant:
173
+
174
  '''
175
 
176
  print("\n\n*** Generate:")
 
181
 
182
  # Inference can also be done using transformers' pipeline
183
 
 
 
 
184
  print("*** Pipeline:")
185
  pipe = pipeline(
186
  "text-generation",
 
194
 
195
  print(pipe(prompt_template)[0]['generated_text'])
196
  ```
197
+ <!-- README_GPTQ.md-use-from-python end -->
198
 
199
+ <!-- README_GPTQ.md-compatibility start -->
200
  ## Compatibility
201
 
202
+ 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).
203
+
204
+ [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.
205
 
206
+ [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
207
+ <!-- README_GPTQ.md-compatibility end -->
208
 
209
  <!-- footer start -->
210
  <!-- 200823 -->
 
229
 
230
  **Special thanks to**: Aemon Algiz.
231
 
232
+ **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
233
 
234
 
235
  Thank you to all my generous patrons and donaters!
 
248
  <figcaption style="font-size: 1em;"><i>"super cute baby alpaca laying on a cloud", Model: epicrealism_pureEvolutionV3</i></figcaption>
249
  </figure>
250
 
 
 
 
 
251
  AlpacaCielo-13b is a llama-2 based model designed for creative tasks, such as storytelling and roleplay, while still doing well with other chatbot purposes. It is a triple model merge of Nous-Hermes + Guanaco + Storywriter. While it is mostly *"uncensored"*, it still inherits some alignment from Guanaco.
252
 
253
+ [GPTQ quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GPTQ)<br>
254
+ [GGML quants](https://huggingface.co/TheBloke/AlpacaCielo-13B-GGML)<br>
255
+ (Courtesy of TheBloke)
256
+
257
+ **Prompt format is this (Guanaco QLORA in oobabooga):**
258
 
259
  ```
260
  ### Human: {prompt}