TheBloke commited on
Commit
2dae6c5
1 Parent(s): 6bbc363

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -16
README.md CHANGED
@@ -1,13 +1,25 @@
1
  ---
 
2
  datasets:
3
  - mlabonne/guanaco-llama2-1k
4
  inference: false
5
  license: llama2
6
  model_creator: MayaPH
7
- model_link: https://huggingface.co/MayaPH/GodziLLa2-70B
8
  model_name: GodziLLa2 70B
9
  model_type: llama
10
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
 
 
 
11
  quantized_by: TheBloke
12
  tags:
13
  - merge
@@ -47,9 +59,9 @@ 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/GodziLLa2-70B-GPTQ)
51
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/GodziLLa2-70B-GGUF)
52
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/GodziLLa2-70B-GGML)
53
  * [MayaPH's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/MayaPH/GodziLLa2-70B)
54
  <!-- repositories-available end -->
55
 
@@ -68,6 +80,7 @@ Below is an instruction that describes a task. Write a response that appropriate
68
 
69
  <!-- prompt-template end -->
70
 
 
71
  <!-- README_GPTQ.md-provided-files start -->
72
  ## Provided files and GPTQ parameters
73
 
@@ -92,22 +105,22 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
92
 
93
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
94
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
95
- | [main](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
96
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
97
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
98
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
99
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
100
- | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
101
 
102
  <!-- README_GPTQ.md-provided-files end -->
103
 
104
  <!-- README_GPTQ.md-download-from-branches start -->
105
  ## How to download from branches
106
 
107
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/GodziLLa2-70B-GPTQ:gptq-4bit-32g-actorder_True`
108
  - With Git, you can clone a branch with:
109
  ```
110
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/GodziLLa2-70B-GPTQ
111
  ```
112
  - In Python Transformers code, the branch is the `revision` parameter; see below.
113
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -120,7 +133,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
120
 
121
  1. Click the **Model tab**.
122
  2. Under **Download custom model or LoRA**, enter `TheBloke/GodziLLa2-70B-GPTQ`.
123
- - To download from a specific branch, enter for example `TheBloke/GodziLLa2-70B-GPTQ:gptq-4bit-32g-actorder_True`
124
  - see Provided Files above for the list of branches for each option.
125
  3. Click **Download**.
126
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -168,10 +181,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
168
 
169
  model_name_or_path = "TheBloke/GodziLLa2-70B-GPTQ"
170
  # To use a different branch, change revision
171
- # For example: revision="gptq-4bit-32g-actorder_True"
172
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
173
- torch_dtype=torch.float16,
174
  device_map="auto",
 
175
  revision="main")
176
 
177
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
@@ -189,7 +202,7 @@ prompt_template=f'''Below is an instruction that describes a task. Write a respo
189
  print("\n\n*** Generate:")
190
 
191
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
192
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
193
  print(tokenizer.decode(output[0]))
194
 
195
  # Inference can also be done using transformers' pipeline
@@ -200,9 +213,11 @@ pipe = pipeline(
200
  model=model,
201
  tokenizer=tokenizer,
202
  max_new_tokens=512,
 
203
  temperature=0.7,
204
  top_p=0.95,
205
- repetition_penalty=1.15
 
206
  )
207
 
208
  print(pipe(prompt_template)[0]['generated_text'])
@@ -227,10 +242,12 @@ For further support, and discussions on these models and AI in general, join us
227
 
228
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
229
 
230
- ## Thanks, and how to contribute.
231
 
232
  Thanks to the [chirper.ai](https://chirper.ai) team!
233
 
 
 
234
  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.
235
 
236
  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.
@@ -242,7 +259,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
242
 
243
  **Special thanks to**: Aemon Algiz.
244
 
245
- **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
246
 
247
 
248
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/MayaPH/GodziLLa2-70B
3
  datasets:
4
  - mlabonne/guanaco-llama2-1k
5
  inference: false
6
  license: llama2
7
  model_creator: MayaPH
 
8
  model_name: GodziLLa2 70B
9
  model_type: llama
10
  pipeline_tag: text-generation
11
+ prompt_template: 'Below is an instruction that describes a task. Write a response
12
+ that appropriately completes the request.
13
+
14
+
15
+ ### Instruction:
16
+
17
+ {prompt}
18
+
19
+
20
+ ### Response:
21
+
22
+ '
23
  quantized_by: TheBloke
24
  tags:
25
  - merge
 
59
  <!-- repositories-available start -->
60
  ## Repositories available
61
 
62
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/GodziLLa2-70B-AWQ)
63
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/GodziLLa2-70B-GPTQ)
64
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/GodziLLa2-70B-GGUF)
 
65
  * [MayaPH's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/MayaPH/GodziLLa2-70B)
66
  <!-- repositories-available end -->
67
 
 
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/GodziLLa2-70B-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. |
109
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
110
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
111
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
112
  | [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.77 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
113
+ | [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/GodziLLa2-70B-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. |
114
 
115
  <!-- README_GPTQ.md-provided-files end -->
116
 
117
  <!-- README_GPTQ.md-download-from-branches start -->
118
  ## How to download from branches
119
 
120
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/GodziLLa2-70B-GPTQ:main`
121
  - With Git, you can clone a branch with:
122
  ```
123
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/GodziLLa2-70B-GPTQ
124
  ```
125
  - In Python Transformers code, the branch is the `revision` parameter; see below.
126
  <!-- README_GPTQ.md-download-from-branches end -->
 
133
 
134
  1. Click the **Model tab**.
135
  2. Under **Download custom model or LoRA**, enter `TheBloke/GodziLLa2-70B-GPTQ`.
136
+ - To download from a specific branch, enter for example `TheBloke/GodziLLa2-70B-GPTQ:main`
137
  - see Provided Files above for the list of branches for each option.
138
  3. Click **Download**.
139
  4. The model will start downloading. Once it's finished it will say "Done".
 
181
 
182
  model_name_or_path = "TheBloke/GodziLLa2-70B-GPTQ"
183
  # To use a different branch, change revision
184
+ # For example: revision="main"
185
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
186
  device_map="auto",
187
+ trust_remote_code=False,
188
  revision="main")
189
 
190
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
202
  print("\n\n*** Generate:")
203
 
204
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
205
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
206
  print(tokenizer.decode(output[0]))
207
 
208
  # Inference can also be done using transformers' pipeline
 
213
  model=model,
214
  tokenizer=tokenizer,
215
  max_new_tokens=512,
216
+ do_sample=True,
217
  temperature=0.7,
218
  top_p=0.95,
219
+ top_k=40,
220
+ repetition_penalty=1.1
221
  )
222
 
223
  print(pipe(prompt_template)[0]['generated_text'])
 
242
 
243
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
244
 
245
+ ## Thanks, and how to contribute
246
 
247
  Thanks to the [chirper.ai](https://chirper.ai) team!
248
 
249
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
250
+
251
  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.
252
 
253
  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.
 
259
 
260
  **Special thanks to**: Aemon Algiz.
261
 
262
+ **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
263
 
264
 
265
  Thank you to all my generous patrons and donaters!