huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-16 10:38:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

s/candle/candle_core/g

Browse Source
This commit is contained in:
Nicolas Patry
2023-08-02 18:35:31 +02:00
parent ae68635af9
commit 166f4d1101
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
candle-book/src/inference/hub.md
View File

@ -10,17 +10,17 @@ Then let's start by downloading the [model file](https://huggingface.co/bert-bas
```rust
# extern crate candle;
# extern crate candle_core;
# extern crate hf_hub;
use hf_hub::api::sync::Api;
use candle::Device;
use candle_core::Device;
let api = Api::new().unwrap();
let repo = api.model("bert-base-uncased".to_string());
let weights = repo.get("model.safetensors").unwrap();
let weights = candle::safetensors::load(weights, &Device::Cpu);
let weights = candle_core::safetensors::load(weights, &Device::Cpu);
```
We now have access to all the [tensors](https://huggingface.co/bert-base-uncased?show_tensors=true) within the file.
@ -48,7 +48,7 @@ cargo add hf-hub --features tokio
Now that we have our weights, we can use them in our bert architecture:
```rust
# extern crate candle;
# extern crate candle_core;
# extern crate candle_nn;
# extern crate hf_hub;
# use hf_hub::api::sync::Api;
@ -57,10 +57,10 @@ Now that we have our weights, we can use them in our bert architecture:
# let repo = api.model("bert-base-uncased".to_string());
#
# let weights = repo.get("model.safetensors").unwrap();
use candle::{Device, Tensor, DType};
use candle_core::{Device, Tensor, DType};
use candle_nn::Linear;
let weights = candle::safetensors::load(weights, &Device::Cpu).unwrap();
let weights = candle_core::safetensors::load(weights, &Device::Cpu).unwrap();
let weight = weights.get("bert.encoder.layer.0.attention.self.query.weight").unwrap();
let bias = weights.get("bert.encoder.layer.0.attention.self.query.bias").unwrap();