TheBloke commited on
Commit
3742d6e
1 Parent(s): 51a754c

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -18
README.md CHANGED
@@ -1,14 +1,27 @@
1
  ---
 
2
  datasets:
3
  - jerryjalapeno/nart-100k-synthetic
4
  inference: false
5
  language:
6
  - en
7
- license: llama2
8
  model_creator: Feynman Innovations
9
- model_link: https://huggingface.co/ajibawa-2023/carl-llama-2-13b
10
  model_name: Carl Llama 2
11
  model_type: llama
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  quantized_by: TheBloke
13
  ---
14
 
@@ -44,9 +57,9 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
44
  <!-- repositories-available start -->
45
  ## Repositories available
46
 
 
47
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Carl-Llama-2-13B-GPTQ)
48
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Carl-Llama-2-13B-GGUF)
49
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/ajibawa-2023/carl-llama-2-13b)
50
  * [Feynman Innovations's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ajibawa-2023/carl-llama-2-13b)
51
  <!-- repositories-available end -->
52
 
@@ -64,7 +77,15 @@ CARL:
64
  ```
65
 
66
  <!-- prompt-template end -->
 
 
 
 
67
 
 
 
 
 
68
  <!-- README_GPTQ.md-provided-files start -->
69
  ## Provided files and GPTQ parameters
70
 
@@ -89,22 +110,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
89
 
90
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
91
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
92
- | [main](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
93
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
94
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
95
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
96
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
97
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
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/Carl-Llama-2-13B-GPTQ:gptq-4bit-32g-actorder_True`
105
  - With Git, you can clone a branch with:
106
  ```
107
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Carl-Llama-2-13B-GPTQ
108
  ```
109
  - In Python Transformers code, the branch is the `revision` parameter; see below.
110
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -117,7 +138,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
117
 
118
  1. Click the **Model tab**.
119
  2. Under **Download custom model or LoRA**, enter `TheBloke/Carl-Llama-2-13B-GPTQ`.
120
- - To download from a specific branch, enter for example `TheBloke/Carl-Llama-2-13B-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".
@@ -165,10 +186,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
165
 
166
  model_name_or_path = "TheBloke/Carl-Llama-2-13B-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.bfloat16,
171
  device_map="auto",
 
172
  revision="main")
173
 
174
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -186,7 +207,7 @@ CARL:
186
  print("\n\n*** Generate:")
187
 
188
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
189
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
190
  print(tokenizer.decode(output[0]))
191
 
192
  # Inference can also be done using transformers' pipeline
@@ -197,9 +218,11 @@ pipe = pipeline(
197
  model=model,
198
  tokenizer=tokenizer,
199
  max_new_tokens=512,
 
200
  temperature=0.7,
201
  top_p=0.95,
202
- repetition_penalty=1.15
 
203
  )
204
 
205
  print(pipe(prompt_template)[0]['generated_text'])
@@ -224,10 +247,12 @@ For further support, and discussions on these models and AI in general, join us
224
 
225
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
226
 
227
- ## Thanks, and how to contribute.
228
 
229
  Thanks to the [chirper.ai](https://chirper.ai) team!
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.
@@ -239,7 +264,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
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!
 
1
  ---
2
+ base_model: https://huggingface.co/ajibawa-2023/carl-llama-2-13b
3
  datasets:
4
  - jerryjalapeno/nart-100k-synthetic
5
  inference: false
6
  language:
7
  - en
8
+ license: cc-by-nc-nd-4.0
9
  model_creator: Feynman Innovations
 
10
  model_name: Carl Llama 2
11
  model_type: llama
12
+ prompt_template: 'This is a conversation with your Therapist AI, Carl. Carl is designed
13
+ to help you while in stress. It can answer your questions and help you to calm down
14
+
15
+
16
+ Context
17
+
18
+ You are Carl, A Therapist AI
19
+
20
+ USER: {prompt}
21
+
22
+ CARL:
23
+
24
+ '
25
  quantized_by: TheBloke
26
  ---
27
 
 
57
  <!-- repositories-available start -->
58
  ## Repositories available
59
 
60
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Carl-Llama-2-13B-AWQ)
61
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Carl-Llama-2-13B-GPTQ)
62
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Carl-Llama-2-13B-GGUF)
 
63
  * [Feynman Innovations's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ajibawa-2023/carl-llama-2-13b)
64
  <!-- repositories-available end -->
65
 
 
77
  ```
78
 
79
  <!-- prompt-template end -->
80
+ <!-- licensing start -->
81
+ ## Licensing
82
+
83
+ The creator of the source model has listed its license as `cc-by-nc-nd-4.0`, and this quantization has therefore used that same license.
84
 
85
+ As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
86
+
87
+ In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Feynman Innovations's Carl Llama 2](https://huggingface.co/ajibawa-2023/carl-llama-2-13b).
88
+ <!-- licensing end -->
89
  <!-- README_GPTQ.md-provided-files start -->
90
  ## Provided files and GPTQ parameters
91
 
 
110
 
111
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
112
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
113
+ | [main](https://huggingface.co/TheBloke/Carl-Llama-2-13B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, without Act Order and group size 128g. |
114
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
115
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
116
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
117
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
118
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Carl-Llama-2-13B-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. |
119
 
120
  <!-- README_GPTQ.md-provided-files end -->
121
 
122
  <!-- README_GPTQ.md-download-from-branches start -->
123
  ## How to download from branches
124
 
125
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Carl-Llama-2-13B-GPTQ:main`
126
  - With Git, you can clone a branch with:
127
  ```
128
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/Carl-Llama-2-13B-GPTQ
129
  ```
130
  - In Python Transformers code, the branch is the `revision` parameter; see below.
131
  <!-- README_GPTQ.md-download-from-branches end -->
 
138
 
139
  1. Click the **Model tab**.
140
  2. Under **Download custom model or LoRA**, enter `TheBloke/Carl-Llama-2-13B-GPTQ`.
141
+ - To download from a specific branch, enter for example `TheBloke/Carl-Llama-2-13B-GPTQ:main`
142
  - see Provided Files above for the list of branches for each option.
143
  3. Click **Download**.
144
  4. The model will start downloading. Once it's finished it will say "Done".
 
186
 
187
  model_name_or_path = "TheBloke/Carl-Llama-2-13B-GPTQ"
188
  # To use a different branch, change revision
189
+ # For example: revision="main"
190
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
191
  device_map="auto",
192
+ trust_remote_code=False,
193
  revision="main")
194
 
195
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
207
  print("\n\n*** Generate:")
208
 
209
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
210
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
211
  print(tokenizer.decode(output[0]))
212
 
213
  # Inference can also be done using transformers' pipeline
 
218
  model=model,
219
  tokenizer=tokenizer,
220
  max_new_tokens=512,
221
+ do_sample=True,
222
  temperature=0.7,
223
  top_p=0.95,
224
+ top_k=40,
225
+ repetition_penalty=1.1
226
  )
227
 
228
  print(pipe(prompt_template)[0]['generated_text'])
 
247
 
248
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
249
 
250
+ ## Thanks, and how to contribute
251
 
252
  Thanks to the [chirper.ai](https://chirper.ai) team!
253
 
254
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
255
+
256
  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.
257
 
258
  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.
 
264
 
265
  **Special thanks to**: Aemon Algiz.
266
 
267
+ **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
268
 
269
 
270
  Thank you to all my generous patrons and donaters!