TheBloke commited on
Commit
0ee08e4
1 Parent(s): c1b6f8c

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +29 -16
README.md CHANGED
@@ -1,12 +1,20 @@
1
  ---
 
2
  datasets:
3
  - ehartford/wizard_vicuna_70k_unfiltered
4
  inference: false
5
  license: llama2
6
  model_creator: Jarrad Hope
7
- model_link: https://huggingface.co/jarradh/llama2_70b_chat_uncensored
8
  model_name: Llama2 70B Chat Uncensored
9
  model_type: llama
 
 
 
 
 
 
 
 
10
  quantized_by: TheBloke
11
  tags:
12
  - uncensored
@@ -47,9 +55,9 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
47
  <!-- repositories-available start -->
48
  ## Repositories available
49
 
 
50
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ)
51
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GGUF)
52
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GGML)
53
  * [Jarrad Hope's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jarradh/llama2_70b_chat_uncensored)
54
  <!-- repositories-available end -->
55
 
@@ -66,6 +74,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
66
 
67
  <!-- prompt-template end -->
68
 
 
69
  <!-- README_GPTQ.md-provided-files start -->
70
  ## Provided files and GPTQ parameters
71
 
@@ -90,22 +99,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
90
 
91
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
92
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
93
- | [main](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
94
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. Poor AutoGPTQ CUDA speed. |
95
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 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. |
96
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 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. |
97
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.78 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
98
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
99
 
100
  <!-- README_GPTQ.md-provided-files end -->
101
 
102
  <!-- README_GPTQ.md-download-from-branches start -->
103
  ## How to download from branches
104
 
105
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/llama2_70b_chat_uncensored-GPTQ:gptq-4bit-32g-actorder_True`
106
  - With Git, you can clone a branch with:
107
  ```
108
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ
109
  ```
110
  - In Python Transformers code, the branch is the `revision` parameter; see below.
111
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -118,7 +127,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
118
 
119
  1. Click the **Model tab**.
120
  2. Under **Download custom model or LoRA**, enter `TheBloke/llama2_70b_chat_uncensored-GPTQ`.
121
- - To download from a specific branch, enter for example `TheBloke/llama2_70b_chat_uncensored-GPTQ:gptq-4bit-32g-actorder_True`
122
  - see Provided Files above for the list of branches for each option.
123
  3. Click **Download**.
124
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -166,10 +175,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
166
 
167
  model_name_or_path = "TheBloke/llama2_70b_chat_uncensored-GPTQ"
168
  # To use a different branch, change revision
169
- # For example: revision="gptq-4bit-32g-actorder_True"
170
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
171
- torch_dtype=torch.float16,
172
  device_map="auto",
 
173
  revision="main")
174
 
175
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -185,7 +194,7 @@ prompt_template=f'''### HUMAN:
185
  print("\n\n*** Generate:")
186
 
187
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
188
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
189
  print(tokenizer.decode(output[0]))
190
 
191
  # Inference can also be done using transformers' pipeline
@@ -196,9 +205,11 @@ pipe = pipeline(
196
  model=model,
197
  tokenizer=tokenizer,
198
  max_new_tokens=512,
 
199
  temperature=0.7,
200
  top_p=0.95,
201
- repetition_penalty=1.15
 
202
  )
203
 
204
  print(pipe(prompt_template)[0]['generated_text'])
@@ -223,10 +234,12 @@ For further support, and discussions on these models and AI in general, join us
223
 
224
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
225
 
226
- ## Thanks, and how to contribute.
227
 
228
  Thanks to the [chirper.ai](https://chirper.ai) team!
229
 
 
 
230
  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.
231
 
232
  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.
@@ -238,7 +251,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
238
 
239
  **Special thanks to**: Aemon Algiz.
240
 
241
- **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
242
 
243
 
244
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/jarradh/llama2_70b_chat_uncensored
3
  datasets:
4
  - ehartford/wizard_vicuna_70k_unfiltered
5
  inference: false
6
  license: llama2
7
  model_creator: Jarrad Hope
 
8
  model_name: Llama2 70B Chat Uncensored
9
  model_type: llama
10
+ prompt_template: '### HUMAN:
11
+
12
+ {prompt}
13
+
14
+
15
+ ### RESPONSE:
16
+
17
+ '
18
  quantized_by: TheBloke
19
  tags:
20
  - uncensored
 
55
  <!-- repositories-available start -->
56
  ## Repositories available
57
 
58
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-AWQ)
59
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ)
60
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GGUF)
 
61
  * [Jarrad Hope's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jarradh/llama2_70b_chat_uncensored)
62
  <!-- repositories-available end -->
63
 
 
74
 
75
  <!-- prompt-template end -->
76
 
77
+
78
  <!-- README_GPTQ.md-provided-files start -->
79
  ## Provided files and GPTQ parameters
80
 
 
99
 
100
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
101
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
102
+ | [main](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
103
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
104
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
105
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
106
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.78 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
107
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
108
 
109
  <!-- README_GPTQ.md-provided-files end -->
110
 
111
  <!-- README_GPTQ.md-download-from-branches start -->
112
  ## How to download from branches
113
 
114
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/llama2_70b_chat_uncensored-GPTQ:main`
115
  - With Git, you can clone a branch with:
116
  ```
117
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/llama2_70b_chat_uncensored-GPTQ
118
  ```
119
  - In Python Transformers code, the branch is the `revision` parameter; see below.
120
  <!-- README_GPTQ.md-download-from-branches end -->
 
127
 
128
  1. Click the **Model tab**.
129
  2. Under **Download custom model or LoRA**, enter `TheBloke/llama2_70b_chat_uncensored-GPTQ`.
130
+ - To download from a specific branch, enter for example `TheBloke/llama2_70b_chat_uncensored-GPTQ:main`
131
  - see Provided Files above for the list of branches for each option.
132
  3. Click **Download**.
133
  4. The model will start downloading. Once it's finished it will say "Done".
 
175
 
176
  model_name_or_path = "TheBloke/llama2_70b_chat_uncensored-GPTQ"
177
  # To use a different branch, change revision
178
+ # For example: revision="main"
179
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
180
  device_map="auto",
181
+ trust_remote_code=False,
182
  revision="main")
183
 
184
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
194
  print("\n\n*** Generate:")
195
 
196
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
197
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
198
  print(tokenizer.decode(output[0]))
199
 
200
  # Inference can also be done using transformers' pipeline
 
205
  model=model,
206
  tokenizer=tokenizer,
207
  max_new_tokens=512,
208
+ do_sample=True,
209
  temperature=0.7,
210
  top_p=0.95,
211
+ top_k=40,
212
+ repetition_penalty=1.1
213
  )
214
 
215
  print(pipe(prompt_template)[0]['generated_text'])
 
234
 
235
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
236
 
237
+ ## Thanks, and how to contribute
238
 
239
  Thanks to the [chirper.ai](https://chirper.ai) team!
240
 
241
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
242
+
243
  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.
244
 
245
  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.
 
251
 
252
  **Special thanks to**: Aemon Algiz.
253
 
254
+ **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
255
 
256
 
257
  Thank you to all my generous patrons and donaters!