TheBloke commited on
Commit
a17885f
1 Parent(s): 47d28ef

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -42
README.md CHANGED
@@ -3,8 +3,12 @@ inference: false
3
  language:
4
  - en
5
  license: other
 
 
 
6
  model_type: llama
7
  pipeline_tag: text-generation
 
8
  tags:
9
  - facebook
10
  - meta
@@ -14,57 +18,72 @@ tags:
14
  ---
15
 
16
  <!-- header start -->
17
- <div style="width: 100%;">
18
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
19
  </div>
20
  <div style="display: flex; justify-content: space-between; width: 100%;">
21
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
22
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
23
  </div>
24
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
25
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
26
  </div>
27
  </div>
 
 
28
  <!-- header end -->
29
 
30
- # Meta's Llama 2 13B-chat GGML
 
 
31
 
32
- These files are GGML format model files for [Meta's Llama 2 13B-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf).
 
 
 
 
 
 
 
 
 
33
 
34
  GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
35
- * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with full GPU acceleration out of the box. Especially good for story telling.
36
- * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with GPU acceleration via the c_transformers backend.
37
- * [LM Studio](https://lmstudio.ai/), a fully featured local GUI. Supports full GPU accel on macOS. Also supports Windows, without GPU accel.
38
- * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Requires extra steps to enable GPU accel via llama.cpp backend.
39
- * [ctransformers](https://github.com/marella/ctransformers), a Python library with LangChain support and OpenAI-compatible AI server.
40
- * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with OpenAI-compatible API server.
41
 
42
  ## Repositories available
43
 
44
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ)
45
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML)
46
- * [Original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta-llama/Llama-2-13B-chat-hf)
 
47
 
48
  ## Prompt template: Llama-2-Chat
49
 
50
  ```
51
- SYSTEM: You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
52
- USER: {prompt}
53
- ASSISTANT:
 
 
54
  ```
55
 
56
  <!-- compatibility_ggml start -->
57
  ## Compatibility
58
 
59
- ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
60
-
61
- These are guaranteed to be compatible with any UIs, tools and libraries released since late May. They may be phased out soon, as they are largely superseded by the new k-quant methods.
62
 
63
- ### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
64
 
65
- These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
66
 
67
- They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python, ctransformers, rustformers and most others. For compatibility with other tools and libraries, please check their documentation.
68
 
69
  ## Explanation of the new k-quant methods
70
  <details>
@@ -83,43 +102,51 @@ Refer to the Provided Files table below to see what files use which methods, and
83
  <!-- compatibility_ggml end -->
84
 
85
  ## Provided files
 
86
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
87
  | ---- | ---- | ---- | ---- | ---- | ----- |
88
- | llama-2-13b-chat.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB| 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
89
- | llama-2-13b-chat.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB| 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
90
- | llama-2-13b-chat.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB| 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
91
- | llama-2-13b-chat.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB| 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
92
- | llama-2-13b-chat.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB| 9.82 GB | Original quant method, 4-bit. |
93
- | llama-2-13b-chat.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB| 10.64 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
94
- | llama-2-13b-chat.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB| 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
95
- | llama-2-13b-chat.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB| 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
96
- | llama-2-13b-chat.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB| 11.45 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
97
- | llama-2-13b-chat.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB| 12.26 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
98
- | llama-2-13b-chat.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB| 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
99
- | llama-2-13b-chat.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB| 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
100
- | llama-2-13b-chat.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB| 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
101
- | llama-2-13b-chat.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB| 16.33 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
102
 
103
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
104
 
105
  ## How to run in `llama.cpp`
106
 
107
- I use the following command line; adjust for your tastes and needs:
 
 
108
 
109
  ```
110
- ./main -t 10 -ngl 32 -m llama-2-13b-chat.ggmlv3.q4_0.bin --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 --in-prefix-bos --in-prefix ' [INST] ' --in-suffix ' [/INST]' -i -p "[INST] <<SYS>> You are a helpful, respectful and honest assistant. <</SYS>> Write a story about llamas. [/INST]"
111
  ```
112
  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`.
113
 
114
  Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
115
 
 
 
116
  If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
117
 
 
 
118
  ## How to run in `text-generation-webui`
119
 
120
- Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
121
 
122
  <!-- footer start -->
 
123
  ## Discord
124
 
125
  For further support, and discussions on these models and AI in general, join us at:
@@ -139,12 +166,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
139
  * Patreon: https://patreon.com/TheBlokeAI
140
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
141
 
142
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
 
 
143
 
144
- **Patreon special mentions**: Space Cruiser, Nikolai Manek, Sam, Chris McCloskey, Rishabh Srivastava, Kalila, Spiking Neurons AB, Khalefa Al-Ahmad, WelcomeToTheClub, Chadd, Lone Striker, Viktor Bowallius, Edmond Seymore, Ai Maven, Chris Smitley, Dave, Alexandros Triantafyllidis, Luke @flexchar, Elle, ya boyyy, Talal Aujan, Alex , Jonathan Leane, Deep Realms, Randy H, subjectnull, Preetika Verma, Joseph William Delisle, Michael Levine, chris gileta, K, Oscar Rangel, LangChain4j, Trenton Dambrowitz, Eugene Pentland, Johann-Peter Hartmann, Femi Adebogun, Illia Dulskyi, senxiiz, Daniel P. Andersen, Sean Connelly, Artur Olbinski, RoA, Mano Prime, Derek Yates, Raven Klaugh, David Flickinger, Willem Michiel, Pieter, Willian Hasse, vamX, Luke Pendergrass, webtim, Ghost , Rainer Wilmers, Nathan LeClaire, Will Dee, Cory Kujawski, John Detwiler, Fred von Graf, biorpg, Iucharbius , Imad Khwaja, Pierre Kircher, terasurfer , Asp the Wyvern, John Villwock, theTransient, zynix , Gabriel Tamborski, Fen Risland, Gabriel Puliatti, Matthew Berman, Pyrater, SuperWojo, Stephen Murray, Karl Bernard, Ajan Kanaga, Greatston Gnanesh, Junyu Yang.
145
 
146
  Thank you to all my generous patrons and donaters!
147
 
 
 
148
  <!-- footer end -->
149
 
150
  # Original model card: Meta's Llama 2 13B-chat
@@ -182,6 +212,8 @@ Meta developed and publicly released the Llama 2 family of large language models
182
 
183
  **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
184
 
 
 
185
  ## Intended Use
186
  **Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
187
 
 
3
  language:
4
  - en
5
  license: other
6
+ model_creator: Meta Llama 2
7
+ model_link: https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
8
+ model_name: Llama 2 13B Chat
9
  model_type: llama
10
  pipeline_tag: text-generation
11
+ quantized_by: TheBloke
12
  tags:
13
  - facebook
14
  - meta
 
18
  ---
19
 
20
  <!-- header start -->
21
+ <!-- 200823 -->
22
+ <div style="width: auto; margin-left: auto; margin-right: auto">
23
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
24
  </div>
25
  <div style="display: flex; justify-content: space-between; width: 100%;">
26
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
27
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
28
  </div>
29
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
30
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
31
  </div>
32
  </div>
33
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
34
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
35
  <!-- header end -->
36
 
37
+ # Llama 2 13B Chat - GGML
38
+ - Model creator: [Meta Llama 2](https://huggingface.co/meta-llama)
39
+ - Original model: [Llama 2 13B Chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf)
40
 
41
+ ## Description
42
+
43
+ This repo contains GGML format model files for [Meta's Llama 2 13B-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf).
44
+
45
+ ### Important note regarding GGML files.
46
+
47
+ The GGML format has now been superseded by GGUF. As of August 21st 2023, [llama.cpp](https://github.com/ggerganov/llama.cpp) no longer supports GGML models. Third party clients and libraries are expected to still support it for a time, but many may also drop support.
48
+
49
+ Please use the GGUF models instead.
50
+ ### About GGML
51
 
52
  GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
53
+ * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
54
+ * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
55
+ * [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
56
+ * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with CUDA GPU acceleration via the c_transformers backend.
57
+ * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
58
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
59
 
60
  ## Repositories available
61
 
62
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ)
63
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF)
64
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML)
65
+ * [Meta Llama 2's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/meta-llama/Llama-2-13B-chat-hf)
66
 
67
  ## Prompt template: Llama-2-Chat
68
 
69
  ```
70
+ [INST] <<SYS>>
71
+ You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
72
+ <</SYS>>
73
+ {prompt}[/INST]
74
+
75
  ```
76
 
77
  <!-- compatibility_ggml start -->
78
  ## Compatibility
79
 
80
+ These quantised GGML files are compatible with llama.cpp between June 6th (commit `2d43387`) and August 21st 2023.
 
 
81
 
82
+ For support with latest llama.cpp, please use GGUF files instead.
83
 
84
+ The final llama.cpp commit with support for GGML was: [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa)
85
 
86
+ As of August 23rd 2023 they are still compatible with all UIs, libraries and utilities which use GGML. This may change in the future.
87
 
88
  ## Explanation of the new k-quant methods
89
  <details>
 
102
  <!-- compatibility_ggml end -->
103
 
104
  ## Provided files
105
+
106
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
107
  | ---- | ---- | ---- | ---- | ---- | ----- |
108
+ | [llama-2-13b-chat.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q2_K.bin) | q2_K | 2 | 5.51 GB| 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
109
+ | [llama-2-13b-chat.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 5.66 GB| 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
110
+ | [llama-2-13b-chat.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 6.31 GB| 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
111
+ | [llama-2-13b-chat.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 6.93 GB| 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
112
+ | [llama-2-13b-chat.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.32 GB| 9.82 GB | Original quant method, 4-bit. |
113
+ | [llama-2-13b-chat.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 7.37 GB| 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
114
+ | [llama-2-13b-chat.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 7.87 GB| 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
115
+ | [llama-2-13b-chat.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q4_1.bin) | q4_1 | 4 | 8.14 GB| 10.64 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
116
+ | [llama-2-13b-chat.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_0.bin) | q5_0 | 5 | 8.95 GB| 11.45 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
117
+ | [llama-2-13b-chat.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 8.97 GB| 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
118
+ | [llama-2-13b-chat.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 9.23 GB| 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
119
+ | [llama-2-13b-chat.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q5_1.bin) | q5_1 | 5 | 9.76 GB| 12.26 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
120
+ | [llama-2-13b-chat.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q6_K.bin) | q6_K | 6 | 10.68 GB| 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
121
+ | [llama-2-13b-chat.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/blob/main/llama-2-13b-chat.ggmlv3.q8_0.bin) | q8_0 | 8 | 13.83 GB| 16.33 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
122
 
123
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
124
 
125
  ## How to run in `llama.cpp`
126
 
127
+ Make sure you are using `llama.cpp` from commit [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) or earlier.
128
+
129
+ For compatibility with latest llama.cpp, please use GGUF files instead.
130
 
131
  ```
132
+ ./main -t 10 -ngl 32 -m llama-2-13b-chat.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\nWrite a story about llamas[/INST]"
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`.
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 2048` to the desired sequence length for this model. For example, `-c 4096` for a Llama 2 model. For models that use RoPE, add `--rope-freq-base 10000 --rope-freq-scale 0.5` for doubled context, or `--rope-freq-base 10000 --rope-freq-scale 0.25` for 4x context.
139
+
140
  If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
141
 
142
+ For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
143
+
144
  ## How to run in `text-generation-webui`
145
 
146
+ Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
147
 
148
  <!-- footer start -->
149
+ <!-- 200823 -->
150
  ## Discord
151
 
152
  For further support, and discussions on these models and AI in general, join us at:
 
166
  * Patreon: https://patreon.com/TheBlokeAI
167
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
168
 
169
+ **Special thanks to**: Aemon Algiz.
170
+
171
+ **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
172
 
 
173
 
174
  Thank you to all my generous patrons and donaters!
175
 
176
+ And thank you again to a16z for their generous grant.
177
+
178
  <!-- footer end -->
179
 
180
  # Original model card: Meta's Llama 2 13B-chat
 
212
 
213
  **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
214
 
215
+ **Research Paper** ["Llama-2: Open Foundation and Fine-tuned Chat Models"](arxiv.org/abs/2307.09288)
216
+
217
  ## Intended Use
218
  **Intended Use Cases** Llama 2 is intended for commercial and research use in English. Tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
219