TheBloke commited on
Commit
db61512
1 Parent(s): ee57c4a

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -17
README.md CHANGED
@@ -1,14 +1,23 @@
1
  ---
 
2
  inference: false
3
  language:
4
  - fr
5
  library_name: transformers
6
  license: llama2
7
  model_creator: bofenghuang
8
- model_link: https://huggingface.co/bofenghuang/vigogne-2-7b-chat
9
  model_name: Vigogne 2 7B Chat
10
  model_type: llama
11
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
12
  quantized_by: TheBloke
13
  tags:
14
  - LLM
@@ -48,9 +57,9 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
48
  <!-- repositories-available start -->
49
  ## Repositories available
50
 
 
51
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ)
52
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGUF)
53
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGML)
54
  * [bofenghuang's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bofenghuang/vigogne-2-7b-chat)
55
  <!-- repositories-available end -->
56
 
@@ -71,6 +80,7 @@ Vigogne strictly avoids discussing sensitive, offensive, illegal, ethical, or po
71
 
72
  <!-- prompt-template end -->
73
 
 
74
  <!-- README_GPTQ.md-provided-files start -->
75
  ## Provided files and GPTQ parameters
76
 
@@ -95,13 +105,13 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
95
 
96
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
97
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
98
- | [main](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 3.90 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
99
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 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. |
100
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 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. |
101
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 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. |
102
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
103
  | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
104
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 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. |
105
  | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
106
 
107
  <!-- README_GPTQ.md-provided-files end -->
@@ -109,10 +119,10 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
109
  <!-- README_GPTQ.md-download-from-branches start -->
110
  ## How to download from branches
111
 
112
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Vigogne-2-7B-Chat-GPTQ:gptq-4bit-32g-actorder_True`
113
  - With Git, you can clone a branch with:
114
  ```
115
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ
116
  ```
117
  - In Python Transformers code, the branch is the `revision` parameter; see below.
118
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -125,7 +135,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
125
 
126
  1. Click the **Model tab**.
127
  2. Under **Download custom model or LoRA**, enter `TheBloke/Vigogne-2-7B-Chat-GPTQ`.
128
- - To download from a specific branch, enter for example `TheBloke/Vigogne-2-7B-Chat-GPTQ:gptq-4bit-32g-actorder_True`
129
  - see Provided Files above for the list of branches for each option.
130
  3. Click **Download**.
131
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -173,10 +183,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
173
 
174
  model_name_or_path = "TheBloke/Vigogne-2-7B-Chat-GPTQ"
175
  # To use a different branch, change revision
176
- # For example: revision="gptq-4bit-32g-actorder_True"
177
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
178
- torch_dtype=torch.float16,
179
  device_map="auto",
 
180
  revision="main")
181
 
182
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -196,7 +206,7 @@ Vigogne strictly avoids discussing sensitive, offensive, illegal, ethical, or po
196
  print("\n\n*** Generate:")
197
 
198
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
199
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
200
  print(tokenizer.decode(output[0]))
201
 
202
  # Inference can also be done using transformers' pipeline
@@ -207,9 +217,11 @@ pipe = pipeline(
207
  model=model,
208
  tokenizer=tokenizer,
209
  max_new_tokens=512,
 
210
  temperature=0.7,
211
  top_p=0.95,
212
- repetition_penalty=1.15
 
213
  )
214
 
215
  print(pipe(prompt_template)[0]['generated_text'])
@@ -234,10 +246,12 @@ For further support, and discussions on these models and AI in general, join us
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
  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.
242
 
243
  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.
@@ -249,7 +263,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
249
 
250
  **Special thanks to**: Aemon Algiz.
251
 
252
- **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
253
 
254
 
255
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/bofenghuang/vigogne-2-7b-chat
3
  inference: false
4
  language:
5
  - fr
6
  library_name: transformers
7
  license: llama2
8
  model_creator: bofenghuang
 
9
  model_name: Vigogne 2 7B Chat
10
  model_type: llama
11
  pipeline_tag: text-generation
12
+ prompt_template: "Below is a conversation between a user and an AI assistant named\
13
+ \ Vigogne.\nVigogne is polite, emotionally aware, humble-but-knowledgeable, always\
14
+ \ providing helpful and detailed answers.\nVigogne is skilled in responding proficiently\
15
+ \ in the languages its users use and can perform a wide range of tasks such as text\
16
+ \ editing, translation, question answering, logical reasoning, coding, and many\
17
+ \ others.\nVigogne cannot receive or generate audio or visual content and cannot\
18
+ \ access the internet.\nVigogne strictly avoids discussing sensitive, offensive,\
19
+ \ illegal, ethical, or political topics and caveats when unsure of the answer.\n\
20
+ \n<|UTILISATEUR|>: {prompt}\n<|ASSISTANT|>: \n"
21
  quantized_by: TheBloke
22
  tags:
23
  - LLM
 
57
  <!-- repositories-available start -->
58
  ## Repositories available
59
 
60
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-AWQ)
61
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ)
62
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGUF)
 
63
  * [bofenghuang's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bofenghuang/vigogne-2-7b-chat)
64
  <!-- repositories-available end -->
65
 
 
80
 
81
  <!-- prompt-template end -->
82
 
83
+
84
  <!-- README_GPTQ.md-provided-files start -->
85
  ## Provided files and GPTQ parameters
86
 
 
105
 
106
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
107
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
108
+ | [main](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 3.90 GB | Yes | 4-bit, without Act Order and group size 128g. |
109
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 4.28 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
110
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 4.02 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
111
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 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. |
112
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
113
  | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
114
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
115
  | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.1 | [French news](https://huggingface.co/datasets/gustavecortal/diverse_french_news) | 4096 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
116
 
117
  <!-- README_GPTQ.md-provided-files end -->
 
119
  <!-- README_GPTQ.md-download-from-branches start -->
120
  ## How to download from branches
121
 
122
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Vigogne-2-7B-Chat-GPTQ:main`
123
  - With Git, you can clone a branch with:
124
  ```
125
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GPTQ
126
  ```
127
  - In Python Transformers code, the branch is the `revision` parameter; see below.
128
  <!-- README_GPTQ.md-download-from-branches end -->
 
135
 
136
  1. Click the **Model tab**.
137
  2. Under **Download custom model or LoRA**, enter `TheBloke/Vigogne-2-7B-Chat-GPTQ`.
138
+ - To download from a specific branch, enter for example `TheBloke/Vigogne-2-7B-Chat-GPTQ:main`
139
  - see Provided Files above for the list of branches for each option.
140
  3. Click **Download**.
141
  4. The model will start downloading. Once it's finished it will say "Done".
 
183
 
184
  model_name_or_path = "TheBloke/Vigogne-2-7B-Chat-GPTQ"
185
  # To use a different branch, change revision
186
+ # For example: revision="main"
187
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
188
  device_map="auto",
189
+ trust_remote_code=False,
190
  revision="main")
191
 
192
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
206
  print("\n\n*** Generate:")
207
 
208
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
209
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
210
  print(tokenizer.decode(output[0]))
211
 
212
  # Inference can also be done using transformers' pipeline
 
217
  model=model,
218
  tokenizer=tokenizer,
219
  max_new_tokens=512,
220
+ do_sample=True,
221
  temperature=0.7,
222
  top_p=0.95,
223
+ top_k=40,
224
+ repetition_penalty=1.1
225
  )
226
 
227
  print(pipe(prompt_template)[0]['generated_text'])
 
246
 
247
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
248
 
249
+ ## Thanks, and how to contribute
250
 
251
  Thanks to the [chirper.ai](https://chirper.ai) team!
252
 
253
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
254
+
255
  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.
256
 
257
  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.
 
263
 
264
  **Special thanks to**: Aemon Algiz.
265
 
266
+ **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
267
 
268
 
269
  Thank you to all my generous patrons and donaters!