huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-17 19:18:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updating the example to reflect new command lines.

Browse Source
This commit is contained in:
Nicolas Patry
2023-07-14 16:56:33 +02:00
parent 4ed56d7861
commit 2d5e952cf9
1 changed files with 23 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
README.md
View File

@ -8,23 +8,33 @@ let b = Tensor::zeros((3, 4), DType::F32, &Device::Cpu)?;
let c = a.matmul(&b)?; let c = a.matmul(&b)?;
``` ```
## Check out our examples
Check out our [examples](./candle-examples/examples/):
- [Whisper](./candle-examples/examples/whisper/)
- [Llama](./candle-examples/examples/llama/)
- [Bert](./candle-examples/examples/bert/) (Useful for sentence embeddings)
- [Falcon](./candle-examples/examples/falcon/)
```
cargo run --example bert --release
cargo run --example whisper --release
cargo run --example llama --release
cargo run --example falcon --release
```
## Features ## Features
- Simple syntax (looks and like PyTorch) - Simple syntax (looks and like PyTorch)
- CPU and Cuda backends (and M1 support) - CPU and Cuda backends, m1, f16, bf16 (and tentatively wasm)
- Enable serverless (CPU), small and fast deployments - Enable serverless (CPU), small and fast deployments
- Model training - Model training
- Distributed computing (NCCL). - Distributed computing (NCCL).
- Models out of the box (Llama, Whisper, Falcon, ...) - Models out of the box (Llama, Whisper, Falcon, ...)
- Emphasis on enabling users to use custom ops/kernels - Emphasis on enabling users to use custom ops/kernels
## Structure
- [candle-core](./candle-core): Core ops, devices, and `Tensor` struct definition
- [candle-nn](./candle-nn/): Facilities to build real models
- [candle-examples](./candle-examples/): Real-world like examples on how to use the library in real settings
- [candle-kernels](./candle-kernels/): CUDA custom kernels
## How to use ? ## How to use ?
Cheatsheet: Cheatsheet:
@ -44,12 +54,12 @@ Cheatsheet:
| Loading | `weights = torch.load("model.bin")` | TODO (see the examples for now) | | Loading | `weights = torch.load("model.bin")` | TODO (see the examples for now) |
Check out our [examples](./candle-examples/examples/): ## Structure
- [Whisper](./candle-examples/examples/whisper/) - [candle-core](./candle-core): Core ops, devices, and `Tensor` struct definition
- [Llama](./candle-examples/examples/llama/) - [candle-nn](./candle-nn/): Facilities to build real models
- [Bert](./candle-examples/examples/bert/) (Useful for sentence embeddings) - [candle-examples](./candle-examples/): Real-world like examples on how to use the library in real settings
- [Falcon](./candle-examples/examples/falcon/) - [candle-kernels](./candle-kernels/): CUDA custom kernels