Skip to content

Commit

Permalink
fix(docs): correct typos (#662)
Browse files Browse the repository at this point in the history
* docs: fix typos

* Update CHANGELOG.md

* Update README.md

* Update README.md

* Update index.md
  • Loading branch information
HKABIG authored Oct 29, 2023
1 parent 0078db7 commit 2833ccf
Show file tree
Hide file tree
Showing 5 changed files with 7 additions and 7 deletions.
2 changes: 1 addition & 1 deletion clients/vim/doc/tabby.txt
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,6 @@ Keybindings~
`<Tab>` if no completion is shown.

<C-\> Trigger completion if not shown. Dismiss the current
compleiton if shown.
completion if shown.

vim:tw=78:ts=8:noet:ft=help:norl:
2 changes: 1 addition & 1 deletion website/blog/2023-09-30-stream-laziness-in-tabby/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,7 @@ This is where the concept of stream laziness comes into play. We should perform

![Cancellation](./cancellation.png)

## How to handle canellation?
## How to handle cancellation?

The core idea is straightforward: on the server side, we need to listen to the `close` event and check if the connection is still valid before pulling data from the LLM stream.

Expand Down
2 changes: 1 addition & 1 deletion website/blog/2023-10-14-seed-round-release-0-3-0-RAG.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ Today, Tabby stands out as the most popular and user-friendly solution to enable


## Release v0.3.0 - Retrieval Augmented Code Completion 🎁
Tabby also comes to a [v0.3.0 release](https://github.com/TabbyML/tabby/releases/tag/v0.3.0), with the support of retrieval-augmented code completion enabled by default. Enhanced by repo-level retrieval, Tabby gets smarter at your codebase and will quickly reference to a related funcion / code example from another file in your repository.
Tabby also comes to a [v0.3.0 release](https://github.com/TabbyML/tabby/releases/tag/v0.3.0), with the support of retrieval-augmented code completion enabled by default. Enhanced by repo-level retrieval, Tabby gets smarter at your codebase and will quickly reference to a related function / code example from another file in your repository.

A blog series detailing the technical designs of retrieval-augmented code completion will be published soon. Stay tuned!🔔

Expand Down
6 changes: 3 additions & 3 deletions website/blog/2023-10-21-incremental-decoding/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ image: ./twitter-decoding.png
---
# Decode the Decoding in Tabby

In the context of the Transformer model, which is widely used across LLMs, ***decoding*** refers to the process of generating an output sequence from an encoded input. Tabby recenty [implemented ***incremental decoding***](https://github.com/TabbyML/tabby/pull/491) as part of the greedy search. This blog will explain our thoughts behind this 🛠️💡.
In the context of the Transformer model, which is widely used across LLMs, ***decoding*** refers to the process of generating an output sequence from an encoded input. Tabby recently [implemented ***incremental decoding***](https://github.com/TabbyML/tabby/pull/491) as part of the greedy search. This blog will explain our thoughts behind this 🛠️💡.


## Common Decoding Methods
Expand All @@ -21,7 +21,7 @@ numbers = [1, 2, 3, 4, 5]
evens = [x for x in numbers
```

To simplify the scenario, we assume that the language model maintains a probaility distribution as shown below,
To simplify the scenario, we assume that the language model maintains a probability distribution as shown below,

![probability](./probability.png)

Expand Down Expand Up @@ -67,6 +67,6 @@ In the case above, the final decoded string would be `" he llo"` with an awkward
Incremental decoding: ......, 207, 211 -> "......[ hello]"
```

For interested folks, you can refer to Tabby's exact implementation in `IncrementalDecoding` funcion in [`creates/tabby-inference/src/decoding.rs`](https://github.com/TabbyML/tabby/pull/491).
For interested folks, you can refer to Tabby's exact implementation in `IncrementalDecoding` function in [`creates/tabby-inference/src/decoding.rs`](https://github.com/TabbyML/tabby/pull/491).

Have you found our new decoding methods effective? Share your thoughts with us in our [Slack](https://join.slack.com/t/tabbyml/shared_invite/zt-22thejc0z-7ePKeWNCHPX31pEtnT4oYQ) channel 🌍😊!
2 changes: 1 addition & 1 deletion website/docs/installation/hugging-face/index.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ This tutorial is now also available on [Hugging Face](https://huggingface.co/doc

## Your first Tabby Space

In this section, you will learn how to deploy a Tabby Space and use it for yourself or your orgnization.
In this section, you will learn how to deploy a Tabby Space and use it for yourself or your organization.

### Deploy Tabby on Spaces

Expand Down

0 comments on commit 2833ccf

Please sign in to comment.