srush / llama2.rs

A fast llama2 decoder in pure Rust.
MIT License
995 stars 54 forks source link

no `TransformerWeights` in `model` #38

Closed sunnyregion closed 10 months ago

sunnyregion commented 10 months ago

use crate::model::TransformerWeights; | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ no TransformerWeights in model

sunnyregion commented 10 months ago

llama2.rs$ tree src src ├── constants.rs ├── gptq_cuda.rs ├── gptq.ptx ├── gptq.rs ├── gptq_test.rs ├── inference.rs ├── kernel.py ├── lib.rs ├── main.rs ├── models.rs ├── tokenizer.rs └── util.rs

0 directories, 12 files

srush commented 10 months ago

good catch, missed a file. Should be fixed now, let me check the CI.

https://github.com/srush/llama2.rs/pull/39

sunnyregion commented 10 months ago

thx a lot