mirror of
https://gitea.com/mcereda/oam.git
synced 2026-02-08 21:34:25 +00:00
feat(kb/ai): add llm article
This commit is contained in:
@@ -17,8 +17,8 @@ TODO
|
|||||||
|
|
||||||
## Further readings
|
## Further readings
|
||||||
|
|
||||||
|
- [Large Language Model] (LLM)
|
||||||
- [Useful AI]: tools, courses, and more, curated and reviewed by experts.
|
- [Useful AI]: tools, courses, and more, curated and reviewed by experts.
|
||||||
- LLMs: [ChatGPT], [Claude], [Copilot], [Duck AI], [Gemini]
|
|
||||||
|
|
||||||
### Sources
|
### Sources
|
||||||
|
|
||||||
@@ -29,12 +29,9 @@ TODO
|
|||||||
|
|
||||||
<!-- In-article sections -->
|
<!-- In-article sections -->
|
||||||
<!-- Knowledge base -->
|
<!-- Knowledge base -->
|
||||||
|
[Large Language Model]: large%20language%20model.md
|
||||||
|
|
||||||
<!-- Files -->
|
<!-- Files -->
|
||||||
<!-- Upstream -->
|
<!-- Upstream -->
|
||||||
<!-- Others -->
|
<!-- Others -->
|
||||||
[ChatGPT]: https://chatgpt.com/
|
|
||||||
[Claude]: https://claude.ai/
|
|
||||||
[Copilot]: https://copilot.microsoft.com/
|
|
||||||
[Duck AI]: https://duck.ai/c
|
|
||||||
[Gemini]: https://gemini.google.com/
|
|
||||||
[Useful AI]: https://usefulai.com/
|
[Useful AI]: https://usefulai.com/
|
||||||
|
|||||||
104
knowledge base/ai/large language model.md
Normal file
104
knowledge base/ai/large language model.md
Normal file
@@ -0,0 +1,104 @@
|
|||||||
|
# Large language model
|
||||||
|
|
||||||
|
_Language models_ are computational model that can predict sequences in natural language.<br/>
|
||||||
|
Useful for speech recognition, machine translation, natural language generation, optical character recognition, route
|
||||||
|
optimization, handwriting recognition, grammar induction, information retrieval, and other tasks.
|
||||||
|
|
||||||
|
_Large_ language models are predominantly based on transformers trained on large datasets, frequently including texts
|
||||||
|
scraped from the Internet.<br/>
|
||||||
|
They have superseded recurrent neural network-based models.
|
||||||
|
|
||||||
|
<!-- Remove this line to uncomment if used
|
||||||
|
## Table of contents <!-- omit in toc -->
|
||||||
|
|
||||||
|
1. [TL;DR](#tldr)
|
||||||
|
1. [Run LLMs Locally](#run-llms-locally)
|
||||||
|
1. [Further readings](#further-readings)
|
||||||
|
1. [Sources](#sources)
|
||||||
|
|
||||||
|
## TL;DR
|
||||||
|
|
||||||
|
| FIXME | Creator |
|
||||||
|
| --------- | ---------- |
|
||||||
|
| [ChatGPT] | OpenAI |
|
||||||
|
| [Claude] | Anthropic |
|
||||||
|
| [Copilot] | Microsoft |
|
||||||
|
| [Duck AI] | DuckDuckGo |
|
||||||
|
| [Gemini] | Google |
|
||||||
|
| [Grok] | X |
|
||||||
|
| [Llama] | Meta |
|
||||||
|
| [Mistral] | Mistral AI |
|
||||||
|
|
||||||
|
<!-- Uncomment if used
|
||||||
|
<details>
|
||||||
|
<summary>Setup</summary>
|
||||||
|
|
||||||
|
```sh
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
-->
|
||||||
|
|
||||||
|
<!-- Uncomment if used
|
||||||
|
<details>
|
||||||
|
<summary>Usage</summary>
|
||||||
|
|
||||||
|
```sh
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
-->
|
||||||
|
|
||||||
|
<!-- Uncomment if used
|
||||||
|
<details>
|
||||||
|
<summary>Real world use cases</summary>
|
||||||
|
|
||||||
|
```sh
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
-->
|
||||||
|
|
||||||
|
## Run LLMs Locally
|
||||||
|
|
||||||
|
Use one of the following:
|
||||||
|
|
||||||
|
- [Ollama]
|
||||||
|
- [LMStudio]
|
||||||
|
- [vLLM]
|
||||||
|
- [Jan]
|
||||||
|
- [llama.cpp]
|
||||||
|
- [Llamafile]
|
||||||
|
|
||||||
|
## Further readings
|
||||||
|
|
||||||
|
### Sources
|
||||||
|
|
||||||
|
- [Run LLMs Locally: 6 Simple Methods]
|
||||||
|
|
||||||
|
<!--
|
||||||
|
Reference
|
||||||
|
═╬═Time══
|
||||||
|
-->
|
||||||
|
|
||||||
|
<!-- In-article sections -->
|
||||||
|
<!-- Knowledge base -->
|
||||||
|
[LMStudio]: lmstudio.md
|
||||||
|
[Ollama]: ollama.md
|
||||||
|
[vLLM]: vllm.md
|
||||||
|
|
||||||
|
<!-- Files -->
|
||||||
|
<!-- Upstream -->
|
||||||
|
<!-- Others -->
|
||||||
|
[ChatGPT]: https://chatgpt.com/
|
||||||
|
[Claude]: https://claude.ai/
|
||||||
|
[Copilot]: https://copilot.microsoft.com/
|
||||||
|
[Duck AI]: https://duck.ai/
|
||||||
|
[Gemini]: https://gemini.google.com/
|
||||||
|
[Grok]: https://grok.com/
|
||||||
|
[Jan]: https://www.jan.ai/
|
||||||
|
[llama.cpp]: https://github.com/ggml-org/llama.cpp
|
||||||
|
[Llama]: https://www.llama.com/
|
||||||
|
[Llamafile]: https://github.com/mozilla-ai/llamafile
|
||||||
|
[Mistral]: https://mistral.ai/
|
||||||
|
[Run LLMs Locally: 6 Simple Methods]: https://www.datacamp.com/tutorial/run-llms-locally-tutorial
|
||||||
@@ -33,6 +33,7 @@
|
|||||||
|
|
||||||
## Further readings
|
## Further readings
|
||||||
|
|
||||||
|
- [Large Language Model] (LLM)
|
||||||
- [Ollama]
|
- [Ollama]
|
||||||
- [Continue VSCode extension]
|
- [Continue VSCode extension]
|
||||||
|
|
||||||
@@ -47,6 +48,7 @@
|
|||||||
|
|
||||||
<!-- In-article sections -->
|
<!-- In-article sections -->
|
||||||
<!-- Knowledge base -->
|
<!-- Knowledge base -->
|
||||||
|
[Large Language Model]: large%20language%20model.md
|
||||||
[Ollama]: ollama.md
|
[Ollama]: ollama.md
|
||||||
|
|
||||||
<!-- Files -->
|
<!-- Files -->
|
||||||
|
|||||||
67
knowledge base/ai/vllm.md
Normal file
67
knowledge base/ai/vllm.md
Normal file
@@ -0,0 +1,67 @@
|
|||||||
|
# Title
|
||||||
|
|
||||||
|
Open source library for LLM inference and serving.
|
||||||
|
|
||||||
|
<!-- Remove this line to uncomment if used
|
||||||
|
## Table of contents <!-- omit in toc -->
|
||||||
|
|
||||||
|
1. [TL;DR](#tldr)
|
||||||
|
1. [Further readings](#further-readings)
|
||||||
|
1. [Sources](#sources)
|
||||||
|
|
||||||
|
## TL;DR
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Setup</summary>
|
||||||
|
|
||||||
|
```sh
|
||||||
|
pip install 'vllm'
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Usage</summary>
|
||||||
|
|
||||||
|
```sh
|
||||||
|
vllm serve 'meta-llama/Llama-2-7b-hf' --port '8000' --gpu-memory-utilization '0.9'
|
||||||
|
vllm serve 'meta-llama/Llama-2-70b-hf' --tensor-parallel-size '2' --port '8000'
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
<!-- Uncomment if used
|
||||||
|
<details>
|
||||||
|
<summary>Real world use cases</summary>
|
||||||
|
|
||||||
|
```sh
|
||||||
|
```
|
||||||
|
|
||||||
|
</details>
|
||||||
|
-->
|
||||||
|
|
||||||
|
## Further readings
|
||||||
|
|
||||||
|
- [Website]
|
||||||
|
- [Codebase]
|
||||||
|
- [Blog]
|
||||||
|
|
||||||
|
### Sources
|
||||||
|
|
||||||
|
- [Documentation]
|
||||||
|
|
||||||
|
<!--
|
||||||
|
Reference
|
||||||
|
═╬═Time══
|
||||||
|
-->
|
||||||
|
|
||||||
|
<!-- In-article sections -->
|
||||||
|
<!-- Knowledge base -->
|
||||||
|
<!-- Files -->
|
||||||
|
<!-- Upstream -->
|
||||||
|
[Blog]: https://blog.vllm.ai/
|
||||||
|
[Codebase]: https://github.com/vllm-project/vllm
|
||||||
|
[Documentation]: https://docs.vllm.ai/en/
|
||||||
|
[Website]: https://vllm.ai/
|
||||||
|
|
||||||
|
<!-- Others -->
|
||||||
@@ -90,7 +90,7 @@
|
|||||||
| LAN | Local Area Network | |
|
| LAN | Local Area Network | |
|
||||||
| LED | Light Emitting Diode | |
|
| LED | Light Emitting Diode | |
|
||||||
| LIFO | Last In First Out | |
|
| LIFO | Last In First Out | |
|
||||||
| LLM | Large Language Model | |
|
| LLM | [Large Language Model] | |
|
||||||
| M2COTS | Mass Market COTS | Widely available COTS products |
|
| M2COTS | Mass Market COTS | Widely available COTS products |
|
||||||
| MR | Merge Request | Prevalently used in GitLab |
|
| MR | Merge Request | Prevalently used in GitLab |
|
||||||
| NACL | Network ACL | |
|
| NACL | Network ACL | |
|
||||||
@@ -182,6 +182,7 @@
|
|||||||
[fish]: fish.md
|
[fish]: fish.md
|
||||||
[iac]: iac.md
|
[iac]: iac.md
|
||||||
[kubernetes]: kubernetes/README.md
|
[kubernetes]: kubernetes/README.md
|
||||||
|
[Large Language Model]: ai/large%20language%20model.md
|
||||||
[lora]: lora.md
|
[lora]: lora.md
|
||||||
[siem]: siem.md
|
[siem]: siem.md
|
||||||
[snowflake]: snowflake/README.md
|
[snowflake]: snowflake/README.md
|
||||||
|
|||||||
Reference in New Issue
Block a user