TheBloke commited on
Commit
00d0e24
1 Parent(s): dd64d3b

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -15
README.md CHANGED
@@ -1,12 +1,25 @@
1
  ---
 
2
  inference: false
3
  language:
4
  - en
5
- license: llama2
 
6
  model_creator: NousResearch
7
- model_link: https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b
8
  model_name: Nous Hermes Llama 2 13B
9
  model_type: llama
 
 
 
 
 
 
 
 
 
 
 
 
10
  quantized_by: TheBloke
11
  tags:
12
  - llama-2
@@ -47,9 +60,9 @@ 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/Nous-Hermes-Llama2-GPTQ)
51
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGUF)
52
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGML)
53
  * [NousResearch's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
54
  <!-- repositories-available end -->
55
 
@@ -67,7 +80,15 @@ Below is an instruction that describes a task. Write a response that appropriate
67
  ```
68
 
69
  <!-- prompt-template end -->
 
 
 
 
70
 
 
 
 
 
71
  <!-- README_GPTQ.md-provided-files start -->
72
  ## Provided files and GPTQ parameters
73
 
@@ -92,24 +113,24 @@ 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/Nous-Hermes-Llama2-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 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/Nous-Hermes-Llama2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 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/Nous-Hermes-Llama2-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 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/Nous-Hermes-Llama2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 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-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
100
- | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. Poor AutoGPTQ CUDA speed. |
101
  | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
102
- | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements and to improve AutoGPTQ speed. |
103
 
104
  <!-- README_GPTQ.md-provided-files end -->
105
 
106
  <!-- README_GPTQ.md-download-from-branches start -->
107
  ## How to download from branches
108
 
109
- - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Nous-Hermes-Llama2-GPTQ:gptq-4bit-32g-actorder_True`
110
  - With Git, you can clone a branch with:
111
  ```
112
- git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ
113
  ```
114
  - In Python Transformers code, the branch is the `revision` parameter; see below.
115
  <!-- README_GPTQ.md-download-from-branches end -->
@@ -122,7 +143,7 @@ It is strongly recommended to use the text-generation-webui one-click-installers
122
 
123
  1. Click the **Model tab**.
124
  2. Under **Download custom model or LoRA**, enter `TheBloke/Nous-Hermes-Llama2-GPTQ`.
125
- - To download from a specific branch, enter for example `TheBloke/Nous-Hermes-Llama2-GPTQ:gptq-4bit-32g-actorder_True`
126
  - see Provided Files above for the list of branches for each option.
127
  3. Click **Download**.
128
  4. The model will start downloading. Once it's finished it will say "Done".
@@ -170,7 +191,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
170
 
171
  model_name_or_path = "TheBloke/Nous-Hermes-Llama2-GPTQ"
172
  # To use a different branch, change revision
173
- # For example: revision="gptq-4bit-32g-actorder_True"
174
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
175
  device_map="auto",
176
  trust_remote_code=False,
@@ -231,10 +252,12 @@ For further support, and discussions on these models and AI in general, join us
231
 
232
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
233
 
234
- ## Thanks, and how to contribute.
235
 
236
  Thanks to the [chirper.ai](https://chirper.ai) team!
237
 
 
 
238
  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.
239
 
240
  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.
@@ -246,7 +269,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
246
 
247
  **Special thanks to**: Aemon Algiz.
248
 
249
- **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
250
 
251
 
252
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b
3
  inference: false
4
  language:
5
  - en
6
+ license:
7
+ - mit
8
  model_creator: NousResearch
 
9
  model_name: Nous Hermes Llama 2 13B
10
  model_type: llama
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
  - llama-2
 
60
  <!-- repositories-available start -->
61
  ## Repositories available
62
 
63
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-AWQ)
64
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ)
65
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGUF)
 
66
  * [NousResearch's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
67
  <!-- repositories-available end -->
68
 
 
80
  ```
81
 
82
  <!-- prompt-template end -->
83
+ <!-- licensing start -->
84
+ ## Licensing
85
+
86
+ The creator of the source model has listed its license as `['mit']`, and this quantization has therefore used that same license.
87
 
88
+ As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
89
+
90
+ In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Nous Research's Nous Hermes Llama 2 13B](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b).
91
+ <!-- licensing end -->
92
  <!-- README_GPTQ.md-provided-files start -->
93
  ## Provided files and GPTQ parameters
94
 
 
113
 
114
  | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
115
  | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
116
+ | [main](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, without Act Order and group size 128g. |
117
+ | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
118
+ | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
119
+ | [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
120
  | [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.95 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
121
+ | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
122
  | [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
123
+ | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
124
 
125
  <!-- README_GPTQ.md-provided-files end -->
126
 
127
  <!-- README_GPTQ.md-download-from-branches start -->
128
  ## How to download from branches
129
 
130
+ - In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Nous-Hermes-Llama2-GPTQ:main`
131
  - With Git, you can clone a branch with:
132
  ```
133
+ git clone --single-branch --branch main https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GPTQ
134
  ```
135
  - In Python Transformers code, the branch is the `revision` parameter; see below.
136
  <!-- README_GPTQ.md-download-from-branches end -->
 
143
 
144
  1. Click the **Model tab**.
145
  2. Under **Download custom model or LoRA**, enter `TheBloke/Nous-Hermes-Llama2-GPTQ`.
146
+ - To download from a specific branch, enter for example `TheBloke/Nous-Hermes-Llama2-GPTQ:main`
147
  - see Provided Files above for the list of branches for each option.
148
  3. Click **Download**.
149
  4. The model will start downloading. Once it's finished it will say "Done".
 
191
 
192
  model_name_or_path = "TheBloke/Nous-Hermes-Llama2-GPTQ"
193
  # To use a different branch, change revision
194
+ # For example: revision="main"
195
  model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
196
  device_map="auto",
197
  trust_remote_code=False,
 
252
 
253
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
254
 
255
+ ## Thanks, and how to contribute
256
 
257
  Thanks to the [chirper.ai](https://chirper.ai) team!
258
 
259
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
260
+
261
  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.
262
 
263
  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.
 
269
 
270
  **Special thanks to**: Aemon Algiz.
271
 
272
+ **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
273
 
274
 
275
  Thank you to all my generous patrons and donaters!