TheBloke commited on
Commit
509c82b
1 Parent(s): 9adf099

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -18
README.md CHANGED
@@ -1,10 +1,15 @@
1
  ---
 
2
  inference: false
3
- license: llama2
4
  model_creator: Tap
5
- model_link: https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored
6
  model_name: Luna AI Llama2 Uncensored
7
  model_type: llama
 
 
 
 
 
8
  quantized_by: TheBloke
9
  ---
10
 
@@ -42,9 +47,9 @@ Many thanks to William Beauchamp from [Chai](https://chai-research.com/) for pro
42
  <!-- repositories-available start -->
43
  ## Repositories available
44
 
 
45
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ)
46
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF)
47
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGML)
48
  * [Tap's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored)
49
  <!-- repositories-available end -->
50
 
@@ -58,7 +63,15 @@ ASSISTANT:
58
  ```
59
 
60
  <!-- prompt-template end -->
 
 
 
 
61
 
 
 
 
 
62
  <!-- README_GPTQ.md-provided-files start -->
63
  ## Provided files and GPTQ parameters
64
 
@@ -83,13 +96,13 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
83
 
84
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
85
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
86
- | [main](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 3.90 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
87
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
88
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.02 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. |
89
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 3.90 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. |
90
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
91
  | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
92
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
93
  | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
94
 
95
  <!-- README_GPTQ.md-provided-files end -->
@@ -97,10 +110,10 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
97
  <!-- README_GPTQ.md-download-from-branches start -->
98
  ## How to download from branches
99
 
100
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Luna-AI-Llama2-Uncensored-GPTQ:gptq-4bit-32g-actorder_True`
101
  - With Git, you can clone a branch with:
102
  ```
103
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ
104
  ```
105
  - In Python Transformers code, the branch is the `revision` parameter; see below.
106
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -113,7 +126,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
113
 
114
  1. Click the **Model tab**.
115
  2. Under **Download custom model or LoRA**, enter `TheBloke/Luna-AI-Llama2-Uncensored-GPTQ`.
116
- - To download from a specific branch, enter for example `TheBloke/Luna-AI-Llama2-Uncensored-GPTQ:gptq-4bit-32g-actorder_True`
117
  - see Provided Files above for the list of branches for each option.
118
  3. Click **Download**.
119
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -161,10 +174,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
161
 
162
  model_name_or_path = "TheBloke/Luna-AI-Llama2-Uncensored-GPTQ"
163
  # To use a different branch, change revision
164
- # For example: revision="gptq-4bit-32g-actorder_True"
165
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
166
- torch_dtype=torch.float16,
167
  device_map="auto",
 
168
  revision="main")
169
 
170
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -178,7 +191,7 @@ ASSISTANT:
178
  print("\n\n*** Generate:")
179
 
180
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
181
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
182
  print(tokenizer.decode(output[0]))
183
 
184
  # Inference can also be done using transformers' pipeline
@@ -189,9 +202,11 @@ pipe = pipeline(
189
  model=model,
190
  tokenizer=tokenizer,
191
  max_new_tokens=512,
 
192
  temperature=0.7,
193
  top_p=0.95,
194
- repetition_penalty=1.15
 
195
  )
196
 
197
  print(pipe(prompt_template)[0]['generated_text'])
@@ -216,10 +231,12 @@ For further support, and discussions on these models and AI in general, join us
216
 
217
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
218
 
219
- ## Thanks, and how to contribute.
220
 
221
  Thanks to the [chirper.ai](https://chirper.ai) team!
222
 
 
 
223
  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.
224
 
225
  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.
@@ -231,7 +248,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
231
 
232
  **Special thanks to**: Aemon Algiz.
233
 
234
- **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
235
 
236
 
237
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored
3
  inference: false
4
+ license: cc-by-sa-4.0
5
  model_creator: Tap
 
6
  model_name: Luna AI Llama2 Uncensored
7
  model_type: llama
8
+ prompt_template: 'USER: {prompt}
9
+
10
+ ASSISTANT:
11
+
12
+ '
13
  quantized_by: TheBloke
14
  ---
15
 
 
47
  <!-- repositories-available start -->
48
  ## Repositories available
49
 
50
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-AWQ)
51
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ)
52
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF)
 
53
  * [Tap's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored)
54
  <!-- repositories-available end -->
55
 
 
63
  ```
64
 
65
  <!-- prompt-template end -->
66
+ <!-- licensing start -->
67
+ ## Licensing
68
+
69
+ The creator of the source model has listed its license as `cc-by-sa-4.0`, and this quantization has therefore used that same license.
70
 
71
+ 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.
72
+
73
+ In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Tap-M's Luna AI Llama2 Uncensored](https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored).
74
+ <!-- licensing end -->
75
  <!-- README_GPTQ.md-provided-files start -->
76
  ## Provided files and GPTQ parameters
77
 
 
96
 
97
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
98
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
99
+ | [main](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 3.90 GB | Yes | 4-bit, without Act Order and group size 128g. |
100
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
101
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.02 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
102
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 3.90 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
103
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
104
  | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
105
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
106
  | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
107
 
108
  <!-- README_GPTQ.md-provided-files end -->
 
110
  <!-- README_GPTQ.md-download-from-branches start -->
111
  ## How to download from branches
112
 
113
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Luna-AI-Llama2-Uncensored-GPTQ:main`
114
  - With Git, you can clone a branch with:
115
  ```
116
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ
117
  ```
118
  - In Python Transformers code, the branch is the `revision` parameter; see below.
119
  <!-- README_GPTQ.md-download-from-branches end -->
 
126
 
127
  1. Click the **Model tab**.
128
  2. Under **Download custom model or LoRA**, enter `TheBloke/Luna-AI-Llama2-Uncensored-GPTQ`.
129
+ - To download from a specific branch, enter for example `TheBloke/Luna-AI-Llama2-Uncensored-GPTQ:main`
130
  - see Provided Files above for the list of branches for each option.
131
  3. Click **Download**.
132
  4. The model will start downloading. Once it's finished it will say "Done".
 
174
 
175
  model_name_or_path = "TheBloke/Luna-AI-Llama2-Uncensored-GPTQ"
176
  # To use a different branch, change revision
177
+ # For example: revision="main"
178
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
179
  device_map="auto",
180
+ trust_remote_code=False,
181
  revision="main")
182
 
183
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
191
  print("\n\n*** Generate:")
192
 
193
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
194
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
195
  print(tokenizer.decode(output[0]))
196
 
197
  # Inference can also be done using transformers' pipeline
 
202
  model=model,
203
  tokenizer=tokenizer,
204
  max_new_tokens=512,
205
+ do_sample=True,
206
  temperature=0.7,
207
  top_p=0.95,
208
+ top_k=40,
209
+ repetition_penalty=1.1
210
  )
211
 
212
  print(pipe(prompt_template)[0]['generated_text'])
 
231
 
232
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
233
 
234
+ ## Thanks, and how to contribute
235
 
236
  Thanks to the [chirper.ai](https://chirper.ai) team!
237
 
238
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
239
+
240
  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.
241
 
242
  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.
 
248
 
249
  **Special thanks to**: Aemon Algiz.
250
 
251
+ **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
252
 
253
 
254
  Thank you to all my generous patrons and donaters!