TheBloke commited on
Commit
1c3395e
1 Parent(s): f247156

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -16
README.md CHANGED
@@ -1,10 +1,24 @@
1
  ---
 
2
  inference: false
3
  license: llama2
4
  model_creator: WizardLM
5
- model_link: https://huggingface.co/WizardLM/WizardMath-70B-V1.0
6
  model_name: WizardMath 70B V1.0
7
  model_type: llama
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  quantized_by: TheBloke
9
  ---
10
 
@@ -40,9 +54,9 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
40
  <!-- repositories-available start -->
41
  ## Repositories available
42
 
 
43
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ)
44
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GGUF)
45
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GGML)
46
  * [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-70B-V1.0)
47
  <!-- repositories-available end -->
48
 
@@ -63,6 +77,7 @@ Below is an instruction that describes a task. Write a response that appropriate
63
 
64
  <!-- prompt-template end -->
65
 
 
66
  <!-- README_GPTQ.md-provided-files start -->
67
  ## Provided files and GPTQ parameters
68
 
@@ -87,22 +102,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
87
 
88
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
89
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
90
- | [main](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 35.33 GB | Yes | Most compatible option. Good inference speed in AutoGPTQ and GPTQ-for-LLaMa. Lower inference quality than other options. |
91
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 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. |
92
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 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. |
93
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 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. |
94
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 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. |
95
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False but poor AutoGPTQ CUDA speed. |
96
 
97
  <!-- README_GPTQ.md-provided-files end -->
98
 
99
  <!-- README_GPTQ.md-download-from-branches start -->
100
  ## How to download from branches
101
 
102
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/WizardMath-70B-V1.0-GPTQ:gptq-4bit-32g-actorder_True`
103
  - With Git, you can clone a branch with:
104
  ```
105
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ
106
  ```
107
  - In Python Transformers code, the branch is the `revision` parameter; see below.
108
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -115,7 +130,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
115
 
116
  1. Click the **Model tab**.
117
  2. Under **Download custom model or LoRA**, enter `TheBloke/WizardMath-70B-V1.0-GPTQ`.
118
- - To download from a specific branch, enter for example `TheBloke/WizardMath-70B-V1.0-GPTQ:gptq-4bit-32g-actorder_True`
119
  - see Provided Files above for the list of branches for each option.
120
  3. Click **Download**.
121
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -163,10 +178,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
163
 
164
  model_name_or_path = "TheBloke/WizardMath-70B-V1.0-GPTQ"
165
  # To use a different branch, change revision
166
- # For example: revision="gptq-4bit-32g-actorder_True"
167
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
168
- torch_dtype=torch.float16,
169
  device_map="auto",
 
170
  revision="main")
171
 
172
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -186,7 +201,7 @@ prompt_template=f'''Below is an instruction that describes a task. Write a respo
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 +212,11 @@ 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 +241,12 @@ 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 +258,7 @@ 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/WizardLM/WizardMath-70B-V1.0
3
  inference: false
4
  license: llama2
5
  model_creator: WizardLM
 
6
  model_name: WizardMath 70B V1.0
7
  model_type: llama
8
+ prompt_template: 'Below is an instruction that describes a task. Write a response
9
+ that appropriately completes the request.
10
+
11
+
12
+
13
+ ### Instruction:
14
+
15
+ {prompt}
16
+
17
+
18
+
19
+ ### Response: Let''s think step by step.
20
+
21
+ '
22
  quantized_by: TheBloke
23
  ---
24
 
 
54
  <!-- repositories-available start -->
55
  ## Repositories available
56
 
57
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-AWQ)
58
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ)
59
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GGUF)
 
60
  * [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-70B-V1.0)
61
  <!-- repositories-available end -->
62
 
 
77
 
78
  <!-- prompt-template end -->
79
 
80
+
81
  <!-- README_GPTQ.md-provided-files start -->
82
  ## Provided files and GPTQ parameters
83
 
 
102
 
103
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
104
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
105
+ | [main](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 35.33 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
106
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 40.66 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
107
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 37.99 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
108
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 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. |
109
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 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. |
110
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [CamelAI Math](https://huggingface.co/datasets/andersonbcdefg/math) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
111
 
112
  <!-- README_GPTQ.md-provided-files end -->
113
 
114
  <!-- README_GPTQ.md-download-from-branches start -->
115
  ## How to download from branches
116
 
117
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/WizardMath-70B-V1.0-GPTQ:main`
118
  - With Git, you can clone a branch with:
119
  ```
120
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/WizardMath-70B-V1.0-GPTQ
121
  ```
122
  - In Python Transformers code, the branch is the `revision` parameter; see below.
123
  <!-- README_GPTQ.md-download-from-branches end -->
 
130
 
131
  1. Click the **Model tab**.
132
  2. Under **Download custom model or LoRA**, enter `TheBloke/WizardMath-70B-V1.0-GPTQ`.
133
+ - To download from a specific branch, enter for example `TheBloke/WizardMath-70B-V1.0-GPTQ:main`
134
  - see Provided Files above for the list of branches for each option.
135
  3. Click **Download**.
136
  4. The model will start downloading. Once it's finished it will say "Done".
 
178
 
179
  model_name_or_path = "TheBloke/WizardMath-70B-V1.0-GPTQ"
180
  # To use a different branch, change revision
181
+ # For example: revision="main"
182
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
183
  device_map="auto",
184
+ trust_remote_code=False,
185
  revision="main")
186
 
187
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
201
  print("\n\n*** Generate:")
202
 
203
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
204
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
205
  print(tokenizer.decode(output[0]))
206
 
207
  # Inference can also be done using transformers' pipeline
 
212
  model=model,
213
  tokenizer=tokenizer,
214
  max_new_tokens=512,
215
+ do_sample=True,
216
  temperature=0.7,
217
  top_p=0.95,
218
+ top_k=40,
219
+ repetition_penalty=1.1
220
  )
221
 
222
  print(pipe(prompt_template)[0]['generated_text'])
 
241
 
242
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
243
 
244
+ ## Thanks, and how to contribute
245
 
246
  Thanks to the [chirper.ai](https://chirper.ai) team!
247
 
248
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
249
+
250
  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.
251
 
252
  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.
 
258
 
259
  **Special thanks to**: Aemon Algiz.
260
 
261
+ **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
262
 
263
 
264
  Thank you to all my generous patrons and donaters!