huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-17 02:58:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add the starcoder example to the readme. (#268)

Browse Source 
* Add the starcoder example to the readme.

* Tweak.
This commit is contained in:
Laurent Mazare
2023-07-28 13:26:23 +01:00
committed by GitHub
parent 3eb2bc6d07
commit fb84ead8f7
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -13,16 +13,20 @@ println!("{c}");
Check out our [examples](./candle-examples/examples/): Check out our [examples](./candle-examples/examples/):
- [Whisper](./candle-examples/examples/whisper/) - [Whisper](./candle-examples/examples/whisper/): speech recognition model.
- [Llama and Llama-v2](./candle-examples/examples/llama/) - [Llama and Llama-v2](./candle-examples/examples/llama/): general LLM.
- [Bert](./candle-examples/examples/bert/) (Useful for sentence embeddings) - [Falcon](./candle-examples/examples/falcon/): general LLM.
- [Falcon](./candle-examples/examples/falcon/) - [Bert](./candle-examples/examples/bert/): useful for sentence embeddings.
- [StarCoder](./candle-examples/examples/bigcode/): LLM specialized to code
generation.
Run them using the following commands:
``` ```
cargo run --example bert --release
cargo run --example whisper --release cargo run --example whisper --release
cargo run --example llama --release cargo run --example llama --release
cargo run --example falcon --release cargo run --example falcon --release
cargo run --example bert --release
cargo run --example bigcode --release
``` ```
In order to use **CUDA** add `--features cuda` to the example command line. In order to use **CUDA** add `--features cuda` to the example command line.
@ -52,7 +56,7 @@ And then browse to
- WASM support, run your models in a browser. - WASM support, run your models in a browser.
- Model training. - Model training.
- Distributed computing using NCCL. - Distributed computing using NCCL.
- Models out of the box: Llama, Whisper, Falcon, BERT... - Models out of the box: Llama, Whisper, Falcon, StarCoder...
- Embed user-defined ops/kernels, such as [flash-attention - Embed user-defined ops/kernels, such as [flash-attention
v2](https://github.com/LaurentMazare/candle/blob/89ba005962495f2bfbda286e185e9c3c7f5300a3/candle-flash-attn/src/lib.rs#L152). v2](https://github.com/LaurentMazare/candle/blob/89ba005962495f2bfbda286e185e9c3c7f5300a3/candle-flash-attn/src/lib.rs#L152).