doc:llm usage

This commit is contained in:
aries_ckt 2023-08-17 13:20:36 +08:00
parent 5a07a6b9d1
commit b34b8cd883
13 changed files with 93 additions and 70 deletions

View File

@ -22,7 +22,7 @@ WEB_SERVER_PORT=7860
#** LLM MODELS **#
#*******************************************************************#
# LLM_MODEL, see /pilot/configs/model_config.LLM_MODEL_CONFIG
LLM_MODEL=vicuna-13b
LLM_MODEL=vicuna-13b-v1.5
MODEL_SERVER=http://127.0.0.1:8000
LIMIT_MODEL_CONCURRENCY=5
MAX_POSITION_EMBEDDINGS=4096

BIN
assets/kbqa/begin_chat.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 189 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 52 KiB

BIN
assets/kbqa/document.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 95 KiB

BIN
assets/kbqa/embedding.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 81 KiB

BIN
assets/kbqa/prompt.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 175 KiB

BIN
assets/kbqa/tasks.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 87 KiB

BIN
assets/kbqa/upload.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 110 KiB

BIN
assets/llm/dbgpt_llm.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 260 KiB

View File

@ -0,0 +1,2 @@
llama.cpp
==================================

View File

@ -0,0 +1,18 @@
LLM Usage
==================================
DB-GPT provides a management and deployment solution for multiple models. This chapter mainly discusses how to deploy different models.
.. image:: ./assets/llm/dbgpt_llm.jpg
- llama_cpp
- quantization
.. toctree::
:maxdepth: 2
:caption: LLM Usage
:name: llama_cpp
:hidden:
./llama/llama_cpp.md
./quantization/quantization.md

View File

@ -0,0 +1,2 @@
quantization
==================================

View File

@ -8,7 +8,7 @@ msgid ""
msgstr ""
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-08-16 18:31+0800\n"
"POT-Creation-Date: 2023-08-17 13:07+0800\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language: zh_CN\n"
@ -20,341 +20,342 @@ msgstr ""
"Generated-By: Babel 2.12.1\n"
#: ../../getting_started/install/environment/environment.md:1
#: f53e1cd4e7f14be68fe574f62b390e72
msgid "Env Parameter"
#: be341d16f7b24bf4ad123ab78a6d855a
#, fuzzy
msgid "Environment Parameter"
msgstr "Env Parameter"
#: ../../getting_started/install/environment/environment.md:4
#: 47136d85ee0e4d9b95ffbf8333bec51d
#: 46eddb27c90f41548ea9a724bbcebd37
msgid "LLM MODEL Config"
msgstr "LLM MODEL Config"
#: ../../getting_started/install/environment/environment.md:5
#: 3b15da40362e4a0182cfab06d0d7832e
#: 7deaa85df4a04fb098f5994547a8724f
msgid "LLM Model Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG"
msgstr "LLM Model Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG"
#: ../../getting_started/install/environment/environment.md:6
#: d65fcfb91f254be995e26b80a9b369f8
#: 3902801c546547b3a4009df681ef7d52
msgid "LLM_MODEL=vicuna-13b"
msgstr "LLM_MODEL=vicuna-13b"
#: ../../getting_started/install/environment/environment.md:8
#: 5b1a0f7f9b81469ca43a328d18250c2d
#: 84b0fdbfa1544ec28751e9b69b00cc02
msgid "MODEL_SERVER_ADDRESS"
msgstr "MODEL_SERVER_ADDRESS"
#: ../../getting_started/install/environment/environment.md:9
#: 2d99674a9aa44254a54548a746369731
#: 0b430bfab77d405989470d00ca3f6fe0
msgid "MODEL_SERVER=http://127.0.0.1:8000 LIMIT_MODEL_CONCURRENCY"
msgstr "MODEL_SERVER=http://127.0.0.1:8000 LIMIT_MODEL_CONCURRENCY"
#: ../../getting_started/install/environment/environment.md:12
#: 9783efba49c24c38ba7c998fdba1f469
#: b477a25586c546729a93fb6785b7b2ec
msgid "LIMIT_MODEL_CONCURRENCY=5"
msgstr "LIMIT_MODEL_CONCURRENCY=5"
#: ../../getting_started/install/environment/environment.md:14
#: 6c9a05252b114942912c2f4123c6e5aa
#: 1d6ea800af384fff9c265610f71cc94e
msgid "MAX_POSITION_EMBEDDINGS"
msgstr "MAX_POSITION_EMBEDDINGS"
#: ../../getting_started/install/environment/environment.md:16
#: d8e6a0b293c4415b91f1c927c2b9313a
#: 388e758ce4ea4692a4c34294cebce7f2
msgid "MAX_POSITION_EMBEDDINGS=4096"
msgstr "MAX_POSITION_EMBEDDINGS=4096"
#: ../../getting_started/install/environment/environment.md:18
#: b206ac79475a40f3add1fabd26fe2f16
#: 16a307dce1294ceba892ff93ae4e81c0
msgid "QUANTIZE_QLORA"
msgstr "QUANTIZE_QLORA"
#: ../../getting_started/install/environment/environment.md:20
#: fb7702fe165441dfb29d18e20a7d65e5
#: 93ceb2b2fcd5454b82eefb0ae8c7ae77
msgid "QUANTIZE_QLORA=True"
msgstr "QUANTIZE_QLORA=True"
#: ../../getting_started/install/environment/environment.md:22
#: 335beebb5fa34878967385bbe6c6aba6
#: 15ffa35d023a4530b02a85ee6168dd4b
msgid "QUANTIZE_8bit"
msgstr "QUANTIZE_8bit"
#: ../../getting_started/install/environment/environment.md:24
#: 8ee6cf930d284c149eff21215795718c
#: 81df248ac5cb4ab0b13a711505f6a177
msgid "QUANTIZE_8bit=True"
msgstr "QUANTIZE_8bit=True"
#: ../../getting_started/install/environment/environment.md:27
#: ad49e465cfe44d13b7172a50ee335875
#: 15cc7b7d41ad44f0891c1189709f00f1
msgid "LLM PROXY Settings"
msgstr "LLM PROXY Settings"
#: ../../getting_started/install/environment/environment.md:28
#: 5804e5a550694f35ba7b3710b6e053a1
#: e6c1115a39404f11b193a1593bc51a22
msgid "OPENAI Key"
msgstr "OPENAI Key"
#: ../../getting_started/install/environment/environment.md:30
#: 06f7ff947bc14784b304774946b621fa
#: 8157e0a831fe4506a426822b7565e4f6
msgid "PROXY_API_KEY={your-openai-sk}"
msgstr "PROXY_API_KEY={your-openai-sk}"
#: ../../getting_started/install/environment/environment.md:31
#: ae34d3c9a4914ce29744ceb1589b18c9
#: 89b34d00bdb64e738bd9bc8c086b1f02
msgid "PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions"
msgstr "PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions"
#: ../../getting_started/install/environment/environment.md:33
#: 1014a1617e7d46a6bccb28fdb0292134
#: 7a97df730aeb484daf19c8172e61a290
msgid "from https://bard.google.com/ f12-> application-> __Secure-1PSID"
msgstr "from https://bard.google.com/ f12-> application-> __Secure-1PSID"
#: ../../getting_started/install/environment/environment.md:35
#: 551d0dc883f141d4a692a0062c766106
#: d430ddf726a049c0a9e0a9bfd5a6fe0e
msgid "BARD_PROXY_API_KEY={your-bard-token}"
msgstr "BARD_PROXY_API_KEY={your-bard-token}"
#: ../../getting_started/install/environment/environment.md:38
#: c0b88491521c45f0a5320c676b2bb72c
#: 23d6b0da3e7042abb55f6181c4a382d2
msgid "DATABASE SETTINGS"
msgstr "DATABASE SETTINGS"
#: ../../getting_started/install/environment/environment.md:39
#: 831c7cba9b09499a92c4072cae486a93
#: dbae0a2d847f41f5be9396a160ef88d0
msgid "SQLite database (Current default database)"
msgstr "SQLite database (Current default database)"
#: ../../getting_started/install/environment/environment.md:40
#: 2eaaa662918244738f5a91b090b34c57
#: bdb55b7280c341a981e9d338cce53345
msgid "LOCAL_DB_PATH=data/default_sqlite.db"
msgstr "LOCAL_DB_PATH=data/default_sqlite.db"
#: ../../getting_started/install/environment/environment.md:41
#: f2a89570e9334db6b0a274e4880c63ce
#: 739d67927a9d46b28500deba1917916b
msgid "LOCAL_DB_TYPE=sqlite # Database Type default:sqlite"
msgstr "LOCAL_DB_TYPE=sqlite # Database Type default:sqlite"
#: ../../getting_started/install/environment/environment.md:43
#: ed93685f20634c05b8cf11fd0dacce1b
#: eb4717bce6a6483b86d9780d924c5ff1
msgid "MYSQL database"
msgstr "MYSQL database"
#: ../../getting_started/install/environment/environment.md:44
#: 769eb44abb0c4960a40e487bed7c42a0
#: 0f4cdf0ff5dd4ff0b397dfa88541a2e1
msgid "LOCAL_DB_TYPE=mysql"
msgstr "LOCAL_DB_TYPE=mysql"
#: ../../getting_started/install/environment/environment.md:45
#: 03219c94db144664894faddc398bf0ef
#: c971ead492c34487bd766300730a9cba
msgid "LOCAL_DB_USER=root"
msgstr "LOCAL_DB_USER=root"
#: ../../getting_started/install/environment/environment.md:46
#: 951fcfc3621f45a8a12a2dd9c4b171e6
#: 02828b29ad044eeab890a2f8af0e5907
msgid "LOCAL_DB_PASSWORD=aa12345678"
msgstr "LOCAL_DB_PASSWORD=aa12345678"
#: ../../getting_started/install/environment/environment.md:47
#: f60ad85f7deb497c9fe582c735dad911
#: 53dc7f15b3934987b1f4c2e2d0b11299
msgid "LOCAL_DB_HOST=127.0.0.1"
msgstr "LOCAL_DB_HOST=127.0.0.1"
#: ../../getting_started/install/environment/environment.md:48
#: 47500d1a30124f07b612bf1038b6563f
#: 1ac95fc482934247a118bab8dcebeb57
msgid "LOCAL_DB_PORT=3306"
msgstr "LOCAL_DB_PORT=3306"
#: ../../getting_started/install/environment/environment.md:51
#: 13f2e7f37f864f32ae5463a760790f5e
#: 34e46aa926844be19c7196759b03af63
msgid "EMBEDDING SETTINGS"
msgstr "EMBEDDING SETTINGS"
#: ../../getting_started/install/environment/environment.md:52
#: 7a5407c2a32645b1aaaf31237622a404
#: 2b5aa08cc995495e85a1f7dc4f97b5d7
msgid "EMBEDDING MODEL Name, see /pilot/configs/model_config.LLM_MODEL_CONFIG"
msgstr "EMBEDDING模型, 参考see /pilot/configs/model_config.LLM_MODEL_CONFIG"
#: ../../getting_started/install/environment/environment.md:53
#: b4ca40b8dbfe467686d1a2634f2960f9
#: 0de0ca551ed040248406f848feca541d
msgid "EMBEDDING_MODEL=text2vec"
msgstr "EMBEDDING_MODEL=text2vec"
#: ../../getting_started/install/environment/environment.md:55
#: e1644a780b5f4070a27694d6015865e8
#: 43019fb570904c9981eb68f33e64569c
msgid "Embedding Chunk size, default 500"
msgstr "Embedding 切片大小, 默认500"
#: ../../getting_started/install/environment/environment.md:57
#: 9f462ca4c25c4b8bb9809425ec9cfb66
#: 7e3f93854873461286e96887e04167aa
msgid "KNOWLEDGE_CHUNK_SIZE=500"
msgstr "KNOWLEDGE_CHUNK_SIZE=500"
#: ../../getting_started/install/environment/environment.md:59
#: 14ce15c1593b42db99f6b1891f1e8a46
#: 9504f4a59ae74352a524b7741113e2d6
msgid "Embedding Chunk Overlap, default 100"
msgstr "Embedding chunk Overlap, 文本块之间的最大重叠量。保留一些重叠可以保持文本块之间的连续性(例如使用滑动窗口),默认100"
#: ../../getting_started/install/environment/environment.md:60
#: c21856a592924271bf1a655a8d552098
#: 24e6119c2051479bbd9dba71a9c23dbe
msgid "KNOWLEDGE_CHUNK_OVERLAP=100"
msgstr "KNOWLEDGE_CHUNK_OVERLAP=100"
#: ../../getting_started/install/environment/environment.md:62
#: 652b5c9891444333861d49d1f5a0029e
#: 0d180d7f2230442abee901c19526e442
msgid "embeding recall top k,5"
msgstr "embedding 召回topk, 默认5"
#: ../../getting_started/install/environment/environment.md:64
#: 3d4e24e414ac4d2ca44a92a9481abd94
#: a5bb9ab2ba50411cbbe87f7836bfbb6d
msgid "KNOWLEDGE_SEARCH_TOP_SIZE=5"
msgstr "KNOWLEDGE_SEARCH_TOP_SIZE=5"
#: ../../getting_started/install/environment/environment.md:66
#: 1407a7fd19304c15bd5f71cb4e3c5871
#: 183b8dd78cba4ae19bd2e08d69d21e0b
msgid "embeding recall max token ,2000"
msgstr "embedding向量召回最大token, 默认2000"
#: ../../getting_started/install/environment/environment.md:68
#: 1b0a31eaaf554cd087646bf384d5ddbf
#: ce0c711febcb44c18ae0fc858c3718d1
msgid "KNOWLEDGE_SEARCH_MAX_TOKEN=5"
msgstr "KNOWLEDGE_SEARCH_MAX_TOKEN=5"
#: ../../getting_started/install/environment/environment.md:71
#: ../../getting_started/install/environment/environment.md:87
#: 63dd3c374601464e8eae33fd7b2e28cc 94e2b09a85ea4883ab725dcd835ddd42
#: 4cab1f399cc245b4a1a1976d2c4fc926 ec9cec667a1c4473bf9a796a26e1ce20
msgid "Vector Store SETTINGS"
msgstr "Vector Store SETTINGS"
#: ../../getting_started/install/environment/environment.md:72
#: ../../getting_started/install/environment/environment.md:88
#: 3ed000578b014afb9f04fdb64bbc03c4 7f99a645141544b783967ae5f0683087
#: 4dd04aadd46948a5b1dcf01fdb0ef074 bab7d512f33e40cf9e10f0da67e699c8
msgid "Chroma"
msgstr "Chroma"
#: ../../getting_started/install/environment/environment.md:73
#: ../../getting_started/install/environment/environment.md:89
#: 4e9e3e7bb12249bda66f5f87b9f722c4 645cf6085f924837836ec17dc895c498
#: 13eec36741b14e028e2d3859a320826e ab3ffbcf9358401993af636ba9ab2e2d
msgid "VECTOR_STORE_TYPE=Chroma"
msgstr "VECTOR_STORE_TYPE=Chroma"
#: ../../getting_started/install/environment/environment.md:74
#: ../../getting_started/install/environment/environment.md:90
#: 5f0b5c13d8d241de89260842587f029a fa090522f5a941179c1240c2f31a6d6b
#: d15b91e2a2884f23a1dd2d54783b0638 d1f856d571b547098bb0c2a18f9f1979
msgid "MILVUS"
msgstr "MILVUS"
#: ../../getting_started/install/environment/environment.md:75
#: ../../getting_started/install/environment/environment.md:91
#: 95a7301dbcfc42e38933a5b720c58477 e240454173ce4c9b9926cea648d63891
#: 1e165f6c934343c7808459cc7a65bc70 985dd60c2b7d4baaa6601a810a6522d7
msgid "VECTOR_STORE_TYPE=Milvus"
msgstr "VECTOR_STORE_TYPE=Milvus"
#: ../../getting_started/install/environment/environment.md:76
#: ../../getting_started/install/environment/environment.md:92
#: 249a91c0245d42ce891ff0d7217fb0d5 8d8ca097f2ba49af802bbcb5bfe02a8a
#: a1a53f051cee40ed886346a94babd75a d263e8eaee684935a58f0a4fe61c6f0e
msgid "MILVUS_URL=127.0.0.1"
msgstr "MILVUS_URL=127.0.0.1"
#: ../../getting_started/install/environment/environment.md:77
#: ../../getting_started/install/environment/environment.md:93
#: 3180099b455a47aeb45701fbdc5e4e4d 9ebf3daaaa994b20880a77df05c55246
#: 2741a312db1a4c6a8a1c1d62415c5fba d03bbf921ddd4f4bb715fe5610c3d0aa
msgid "MILVUS_PORT=19530"
msgstr "MILVUS_PORT=19530"
#: ../../getting_started/install/environment/environment.md:78
#: ../../getting_started/install/environment/environment.md:94
#: 7a6bf87bbc354d75bfb7cdbb19a79db5 ed7b14490c29444bb6aca8f8052c3fd6
#: d0786490d38c4e4f971cc14f62fe1fc8 e9e0854873dc4c209861ee4eb77d25cd
msgid "MILVUS_USERNAME"
msgstr "MILVUS_USERNAME"
#: ../../getting_started/install/environment/environment.md:79
#: ../../getting_started/install/environment/environment.md:95
#: ca0ea23663d14ca884c35c75f3ec6762 fae03ba65210435fb4e1a840d0bf032c
#: 9a82d07153cc432ebe754b5bc02fde0d a6485c1cfa7d4069a6894c43674c8c2b
msgid "MILVUS_PASSWORD"
msgstr "MILVUS_PASSWORD"
#: ../../getting_started/install/environment/environment.md:80
#: ../../getting_started/install/environment/environment.md:96
#: 4112d34ad70c4e2281b16304cbe7d6b6 ab17c60241b0455580057b895041692c
#: 2f233f32b8ba408a9fbadb21fabb99ec 809b3219dd824485bc2cfc898530d708
msgid "MILVUS_SECURE="
msgstr "MILVUS_SECURE="
#: ../../getting_started/install/environment/environment.md:82
#: ../../getting_started/install/environment/environment.md:98
#: 48909fb9e190460b9c1b95534ffa0424 7e17a2d67a64471ebce8287c6c080afb
#: f00603661f2b42e1bd2bca74ad1e3c31 f378e16fdec44c559e34c6929de812e8
msgid "WEAVIATE"
msgstr "WEAVIATE"
#: ../../getting_started/install/environment/environment.md:83
#: 3cade72e7b5d4befa3fc049cf21521cb
#: da2049ebc6874cf0a6b562e0e2fd9ec7
msgid "VECTOR_STORE_TYPE=Weaviate"
msgstr "VECTOR_STORE_TYPE=Weaviate"
#: ../../getting_started/install/environment/environment.md:84
#: ../../getting_started/install/environment/environment.md:99
#: 264720556c5746a59dadad73427bcabd ff741c65112b45f0bed89390bf33cd03
#: 25f1246629934289aad7ef01c7304097 c9fe0e413d9a4fc8abf86b3ed99e0581
msgid "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network"
msgstr "WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network"
#: ../../getting_started/install/environment/environment.md:102
#: 9536be75496642c6b5302f6afb60c340
#: ba7c9e707f6a4cd6b99e52b58da3ab2d
msgid "Multi-GPU Setting"
msgstr "Multi-GPU Setting"
#: ../../getting_started/install/environment/environment.md:103
#: 5986cb5fb6b34decad59f3a161c23b07
#: 5ca75fdf2c264b2c844d77f659b4f0b3
msgid ""
"See https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-"
"visibility-cuda_visible_devices/ If CUDA_VISIBLE_DEVICES is not "
"configured, all available gpus will be used"
msgstr "参考 https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-"
"visibility-cuda_visible_devices/ 如果 CUDA_VISIBLE_DEVICES没有"
"设置, 会使用所有可用的gpu"
msgstr ""
"参考 https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-"
"cuda_visible_devices/ 如果 CUDA_VISIBLE_DEVICES没有设置, 会使用所有可用的gpu"
#: ../../getting_started/install/environment/environment.md:106
#: 5df0644d4a5f419287a9146eaddaffb6
#: de92eb310aff43fbbbf3c5a116c3b2c6
msgid "CUDA_VISIBLE_DEVICES=0"
msgstr "CUDA_VISIBLE_DEVICES=0"
#: ../../getting_started/install/environment/environment.md:108
#: 885df03d13914ea6a11a74063fc35b0a
#: d2641df6123a442b8e4444ad5f01a9aa
msgid ""
"Optionally, you can also specify the gpu ID to use before the starting "
"command"
msgstr "你也可以通过启动命令设置gpu ID"
#: ../../getting_started/install/environment/environment.md:110
#: 45b1a0051a5c402f863e14dc6fca47e8
#: 76c66179d11a4e5fa369421378609aae
msgid "CUDA_VISIBLE_DEVICES=3,4,5,6"
msgstr "CUDA_VISIBLE_DEVICES=3,4,5,6"
#: ../../getting_started/install/environment/environment.md:112
#: ee9502fea64449e48c59948e8b4ecfb5
#: 29bd0f01fdf540ad98385ea8473f7647
msgid "You can configure the maximum memory used by each GPU."
msgstr "可以设置GPU的最大内存"
#: ../../getting_started/install/environment/environment.md:114
#: af8a98833c064fcfa7260ef0bf889c56
#: 31e5e23838734ba7a2810e2387e6d6a0
msgid "MAX_GPU_MEMORY=16Gib"
msgstr "MAX_GPU_MEMORY=16Gib"
#: ../../getting_started/install/environment/environment.md:117
#: 473f789502f945688862d2d9c9f2b4df
#: 99aa63ab1ae049d9b94536d6a96f3443
msgid "Other Setting"
msgstr "Other Setting"
#: ../../getting_started/install/environment/environment.md:118
#: 04871b36ae4f47edbf20b5abdeb92cb2
#: 3168732183874bffb59a3575d3473d62
msgid "Language Settings(influence prompt language)"
msgstr "Language Settings(涉及prompt语言以及知识切片方式)"
#: ../../getting_started/install/environment/environment.md:119
#: 54b4cba342014d9ca1b35acc13d71e6e
#: 73eb0a96f29b4739bd456faa9cb5033d
msgid "LANGUAGE=en"
msgstr "LANGUAGE=en"
#: ../../getting_started/install/environment/environment.md:120
#: db66e92d5c1447abb725c5286608a646
#: c6646b78c6cf4d25a13108232f5b2046
msgid "LANGUAGE=zh"
msgstr "LANGUAGE=zh"