Transformers
GGUF
English
llama
TheBloke commited on
Commit
f221e0a
1 Parent(s): 38271cf

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -23
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  datasets:
3
  - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
4
  inference: false
@@ -6,9 +7,16 @@ language:
6
  - en
7
  license: llama2
8
  model_creator: Eric Hartford
9
- model_link: https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b
10
  model_name: WizardLM 1.0 Uncensored CodeLlama 34B
11
  model_type: llama
 
 
 
 
 
 
 
 
12
  quantized_by: TheBloke
13
  ---
14
 
@@ -33,31 +41,34 @@ quantized_by: TheBloke
33
  - Model creator: [Eric Hartford](https://huggingface.co/ehartford)
34
  - Original model: [WizardLM 1.0 Uncensored CodeLlama 34B](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b)
35
 
 
36
  ## Description
37
 
38
  This repo contains GGUF format model files for [Eric Hartford's WizardLM 1.0 Uncensored CodeLlama 34B](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b).
39
 
 
40
  <!-- README_GGUF.md-about-gguf start -->
41
  ### About GGUF
42
 
43
- GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
44
 
45
- The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.
46
 
47
- Here are a list of clients and libraries that are known to support GGUF:
48
- * [llama.cpp](https://github.com/ggerganov/llama.cpp).
49
- * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
50
- * [KoboldCpp](https://github.com/LostRuins/koboldcpp), now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
51
- * [LM Studio](https://lmstudio.ai/), version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
52
- * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), should now work, choose the `c_transformers` backend. A great web UI with many interesting features. Supports CUDA GPU acceleration.
53
- * [ctransformers](https://github.com/marella/ctransformers), now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
54
- * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
55
- * [candle](https://github.com/huggingface/candle), added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.
56
 
57
  <!-- README_GGUF.md-about-gguf end -->
58
  <!-- repositories-available start -->
59
  ## Repositories available
60
 
 
61
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GPTQ)
62
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF)
63
  * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b)
@@ -75,12 +86,14 @@ ASSISTANT:
75
  ```
76
 
77
  <!-- prompt-template end -->
 
 
78
  <!-- compatibility_gguf start -->
79
  ## Compatibility
80
 
81
- These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit [6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9](https://github.com/ggerganov/llama.cpp/commit/6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9)
82
 
83
- They are now also compatible with many third party UIs and libraries - please see the list at the top of the README.
84
 
85
  ## Explanation of quantisation methods
86
  <details>
@@ -121,21 +134,75 @@ Refer to the Provided Files table below to see what files use which methods, and
121
 
122
  <!-- README_GGUF.md-provided-files end -->
123
 
124
- <!-- README_GGUF.md-how-to-run start -->
125
- ## Example `llama.cpp` command
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
126
 
127
- Make sure you are using `llama.cpp` from commit [6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9](https://github.com/ggerganov/llama.cpp/commit/6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9) or later.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
128
 
129
- For compatibility with older versions of llama.cpp, or for any third-party libraries or clients that haven't yet updated for GGUF, please use GGML files instead.
130
 
 
 
131
  ```
132
- ./main -t 10 -ngl 32 -m wizardlm-1.0-uncensored-codellama-34b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are a helpful AI assistant.\n\nUSER: Write a story about llamas\nASSISTANT:"
 
 
 
 
 
 
 
 
 
 
 
133
  ```
134
- Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`. If offloading all layers to GPU, set `-t 1`.
135
 
136
  Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
137
 
138
- Change `-c 4096` to the desired sequence length for this model. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
139
 
140
  If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
141
 
@@ -192,10 +259,12 @@ For further support, and discussions on these models and AI in general, join us
192
 
193
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
194
 
195
- ## Thanks, and how to contribute.
196
 
197
  Thanks to the [chirper.ai](https://chirper.ai) team!
198
 
 
 
199
  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.
200
 
201
  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.
@@ -207,7 +276,7 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
207
 
208
  **Special thanks to**: Aemon Algiz.
209
 
210
- **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
211
 
212
 
213
  Thank you to all my generous patrons and donaters!
 
1
  ---
2
+ base_model: https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b
3
  datasets:
4
  - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
5
  inference: false
 
7
  - en
8
  license: llama2
9
  model_creator: Eric Hartford
 
10
  model_name: WizardLM 1.0 Uncensored CodeLlama 34B
11
  model_type: llama
12
+ prompt_template: 'You are a helpful AI assistant.
13
+
14
+
15
+ USER: {prompt}
16
+
17
+ ASSISTANT:
18
+
19
+ '
20
  quantized_by: TheBloke
21
  ---
22
 
 
41
  - Model creator: [Eric Hartford](https://huggingface.co/ehartford)
42
  - Original model: [WizardLM 1.0 Uncensored CodeLlama 34B](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b)
43
 
44
+ <!-- description start -->
45
  ## Description
46
 
47
  This repo contains GGUF format model files for [Eric Hartford's WizardLM 1.0 Uncensored CodeLlama 34B](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b).
48
 
49
+ <!-- description end -->
50
  <!-- README_GGUF.md-about-gguf start -->
51
  ### About GGUF
52
 
53
+ GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
54
 
55
+ Here is an incomplate list of clients and libraries that are known to support GGUF:
56
 
57
+ * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
58
+ * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
59
+ * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
60
+ * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
61
+ * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
62
+ * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
63
+ * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
64
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
65
+ * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
66
 
67
  <!-- README_GGUF.md-about-gguf end -->
68
  <!-- repositories-available start -->
69
  ## Repositories available
70
 
71
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-AWQ)
72
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GPTQ)
73
  * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF)
74
  * [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b)
 
86
  ```
87
 
88
  <!-- prompt-template end -->
89
+
90
+
91
  <!-- compatibility_gguf start -->
92
  ## Compatibility
93
 
94
+ These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
95
 
96
+ They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
97
 
98
  ## Explanation of quantisation methods
99
  <details>
 
134
 
135
  <!-- README_GGUF.md-provided-files end -->
136
 
137
+ <!-- README_GGUF.md-how-to-download start -->
138
+ ## How to download GGUF files
139
+
140
+ **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
141
+
142
+ The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
143
+ - LM Studio
144
+ - LoLLMS Web UI
145
+ - Faraday.dev
146
+
147
+ ### In `text-generation-webui`
148
+
149
+ Under Download Model, you can enter the model repo: TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF and below it, a specific filename to download, such as: wizardlm-1.0-uncensored-codellama-34b.q4_K_M.gguf.
150
+
151
+ Then click Download.
152
+
153
+ ### On the command line, including multiple files at once
154
+
155
+ I recommend using the `huggingface-hub` Python library:
156
+
157
+ ```shell
158
+ pip3 install huggingface-hub>=0.17.1
159
+ ```
160
+
161
+ Then you can download any individual model file to the current directory, at high speed, with a command like this:
162
 
163
+ ```shell
164
+ huggingface-cli download TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF wizardlm-1.0-uncensored-codellama-34b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
165
+ ```
166
+
167
+ <details>
168
+ <summary>More advanced huggingface-cli download usage</summary>
169
+
170
+ You can also download multiple files at once with a pattern:
171
+
172
+ ```shell
173
+ huggingface-cli download TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
174
+ ```
175
+
176
+ For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
177
+
178
+ To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
179
+
180
+ ```shell
181
+ pip3 install hf_transfer
182
+ ```
183
 
184
+ And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
185
 
186
+ ```shell
187
+ HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF wizardlm-1.0-uncensored-codellama-34b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
188
  ```
189
+
190
+ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
191
+ </details>
192
+ <!-- README_GGUF.md-how-to-download end -->
193
+
194
+ <!-- README_GGUF.md-how-to-run start -->
195
+ ## Example `llama.cpp` command
196
+
197
+ Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
198
+
199
+ ```shell
200
+ ./main -ngl 32 -m wizardlm-1.0-uncensored-codellama-34b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are a helpful AI assistant.\n\nUSER: {prompt}\nASSISTANT:"
201
  ```
 
202
 
203
  Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
204
 
205
+ Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
206
 
207
  If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
208
 
 
259
 
260
  [TheBloke AI's Discord server](https://discord.gg/theblokeai)
261
 
262
+ ## Thanks, and how to contribute
263
 
264
  Thanks to the [chirper.ai](https://chirper.ai) team!
265
 
266
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
267
+
268
  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.
269
 
270
  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.
 
276
 
277
  **Special thanks to**: Aemon Algiz.
278
 
279
+ **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
280
 
281
 
282
  Thank you to all my generous patrons and donaters!