TheBloke commited on
Commit
0d4a7a0
1 Parent(s): dedb844

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -14
README.md CHANGED
@@ -1,13 +1,16 @@
1
  ---
 
2
  inference: false
3
  language:
4
  - en
5
  license: llama2
6
  model_creator: Meta
7
- model_link: https://huggingface.co/meta-llama/Llama-2-7b-hf
8
  model_name: Llama 2 7B
9
  model_type: llama
10
  pipeline_tag: text-generation
 
 
 
11
  quantized_by: TheBloke
12
  tags:
13
  - facebook
@@ -49,6 +52,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
49
  <!-- repositories-available start -->
50
  ## Repositories available
51
 
 
52
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-7B-GPTQ)
53
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-7B-GGUF)
54
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Llama-2-7B-GGML)
@@ -65,6 +69,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
65
 
66
  <!-- prompt-template end -->
67
 
 
68
  <!-- README_GPTQ.md-provided-files start -->
69
  ## Provided files and GPTQ parameters
70
 
@@ -89,20 +94,20 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
89
 
90
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
91
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
92
- | [main](https://huggingface.co/TheBloke/Llama-2-7B-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. |
93
- | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-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. |
94
- | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-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. |
95
- | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-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. |
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/Llama-2-7B-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/Llama-2-7B-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 +120,7 @@ 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/Llama-2-7B-GPTQ`.
118
- - To download from a specific branch, enter for example `TheBloke/Llama-2-7B-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 +168,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
163
 
164
  model_name_or_path = "TheBloke/Llama-2-7B-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)
@@ -179,7 +184,7 @@ prompt_template=f'''{prompt}
179
  print("\n\n*** Generate:")
180
 
181
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
182
- output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
183
  print(tokenizer.decode(output[0]))
184
 
185
  # Inference can also be done using transformers' pipeline
@@ -190,9 +195,11 @@ pipe = pipeline(
190
  model=model,
191
  tokenizer=tokenizer,
192
  max_new_tokens=512,
 
193
  temperature=0.7,
194
  top_p=0.95,
195
- repetition_penalty=1.15
 
196
  )
197
 
198
  print(pipe(prompt_template)[0]['generated_text'])
@@ -217,10 +224,12 @@ For further support, and discussions on these models and AI in general, join us
217
 
218
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
219
 
220
- ## Thanks, and how to contribute.
221
 
222
  Thanks to the [chirper.ai](https://chirper.ai) team!
223
 
 
 
224
  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.
225
 
226
  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.
@@ -232,7 +241,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
232
 
233
  **Special thanks to**: Aemon Algiz.
234
 
235
- **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
236
 
237
 
238
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/meta-llama/Llama-2-7b-hf
3
  inference: false
4
  language:
5
  - en
6
  license: llama2
7
  model_creator: Meta
 
8
  model_name: Llama 2 7B
9
  model_type: llama
10
  pipeline_tag: text-generation
11
+ prompt_template: '{prompt}
12
+
13
+ '
14
  quantized_by: TheBloke
15
  tags:
16
  - facebook
 
52
  <!-- repositories-available start -->
53
  ## Repositories available
54
 
55
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Llama-2-7B-AWQ)
56
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-7B-GPTQ)
57
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-7B-GGUF)
58
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Llama-2-7B-GGML)
 
69
 
70
  <!-- prompt-template end -->
71
 
72
+
73
  <!-- README_GPTQ.md-provided-files start -->
74
  ## Provided files and GPTQ parameters
75
 
 
94
 
95
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
96
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
97
+ | [main](https://huggingface.co/TheBloke/Llama-2-7B-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. |
98
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-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. |
99
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-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. |
100
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Llama-2-7B-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. |
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/Llama-2-7B-GPTQ:main`
108
  - With Git, you can clone a branch with:
109
  ```
110
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/Llama-2-7B-GPTQ
111
  ```
112
  - In Python Transformers code, the branch is the `revision` parameter; see below.
113
  <!-- README_GPTQ.md-download-from-branches end -->
 
120
 
121
  1. Click the **Model tab**.
122
  2. Under **Download custom model or LoRA**, enter `TheBloke/Llama-2-7B-GPTQ`.
123
+ - To download from a specific branch, enter for example `TheBloke/Llama-2-7B-GPTQ:main`
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
 
169
  model_name_or_path = "TheBloke/Llama-2-7B-GPTQ"
170
  # To use a different branch, change revision
171
+ # For example: revision="main"
172
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 
173
  device_map="auto",
174
+ trust_remote_code=True,
175
  revision="main")
176
 
177
  tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
184
  print("\n\n*** Generate:")
185
 
186
  input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
187
+ output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
188
  print(tokenizer.decode(output[0]))
189
 
190
  # Inference can also be done using transformers' pipeline
 
195
  model=model,
196
  tokenizer=tokenizer,
197
  max_new_tokens=512,
198
+ do_sample=True,
199
  temperature=0.7,
200
  top_p=0.95,
201
+ top_k=40,
202
+ repetition_penalty=1.1
203
  )
204
 
205
  print(pipe(prompt_template)[0]['generated_text'])
 
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
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
232
+
233
  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.
234
 
235
  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.
 
241
 
242
  **Special thanks to**: Aemon Algiz.
243
 
244
+ **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
245
 
246
 
247
  Thank you to all my generous patrons and donaters!