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

add chat models in quantized example (#551)

Browse Source 
* add chat models in quantized example

* cargo fmt
This commit is contained in:
cksac
2023-08-23 18:05:33 +08:00
committed by GitHub
parent 9a5c7db91a
commit 89a00b56cc
1 changed files with 18 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
candle-examples/examples/quantized/main.rs
View File

@ -391,6 +391,12 @@ enum Which {
L13b,
#[value(name = "70b")]
L70b,
#[value(name = "7b-chat")]
L7bChat,
#[value(name = "13b-chat")]
L13bChat,
#[value(name = "70b-chat")]
L70bChat,
}
#[derive(Parser, Debug)]
@ -466,6 +472,18 @@ impl Args {
Which::L7b => ("TheBloke/Llama-2-7B-GGML", "llama-2-7b.ggmlv3.q4_0.bin"),
Which::L13b => ("TheBloke/Llama-2-13B-GGML", "llama-2-13b.ggmlv3.q4_0.bin"),
Which::L70b => ("TheBloke/Llama-2-70B-GGML", "llama-2-70b.ggmlv3.q4_0.bin"),
Which::L7bChat => (
"TheBloke/Llama-2-7B-Chat-GGML",
"llama-2-7b-chat.ggmlv3.q4_0.bin",
),
Which::L13bChat => (
"TheBloke/Llama-2-13B-Chat-GGML",
"llama-2-13b-chat.ggmlv3.q4_0.bin",
),
Which::L70bChat => (
"TheBloke/Llama-2-70B-Chat-GGML",
"llama-2-70b-chat.ggmlv3.q4_0.bin",
),
};
let api = hf_hub::api::sync::Api::new()?;
let api = api.model(repo.to_string());