Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

support qwen2 gguf architecture #851

Closed
franklucky001 opened this issue Oct 15, 2024 · 4 comments
Closed

support qwen2 gguf architecture #851

franklucky001 opened this issue Oct 15, 2024 · 4 comments
Labels
new feature New feature or request

Comments

@franklucky001
Copy link

run docker

docker run --name mistral \
	-v /home/gxy/modelscope/Qwen2.5-1.5B-Instruct-GGUF:/model \
	-p 8888:80 \
	-e RUST_BACKTRACE=1 \
	-t ericlbuehler/mistral.rs:cpu-latest \
	-i gguf -m /model -f qwen2.5-1.5b-instruct-q4_k_m.gguf

run error

called Result::unwrap() on an Err value: Unknown GGUF architecture qwen2

Stack backtrace:
0: anyhow::error::::msg
1: mistralrs_core::gguf::GGUFArchitecture::from_value
2: mistralrs_core::gguf::content::Content::from_readers
3: <mistralrs_core::pipeline::gguf::GGUFLoader as mistralrs_core::pipeline::loaders::Loader>::load_model_from_path
4: <mistralrs_core::pipeline::gguf::GGUFLoader as mistralrs_core::pipeline::loaders::Loader>::load_model_from_hf
5: mistralrs_server::main::{{closure}}
6: tokio::runtime::park::CachedParkThread::block_on
7: mistralrs_server::main
8: std::sys::backtrace::__rust_begin_short_backtrace
9: std::rt::lang_start::{{closure}}
10: std::rt::lang_start_internal
11: main
12:
13: __libc_start_main
14: _start
stack backtrace:
0: rust_begin_unwind
1: core::panicking::panic_fmt
2: core::result::unwrap_failed
3: mistralrs_core::gguf::content::Content::from_readers
4: <mistralrs_core::pipeline::gguf::GGUFLoader as mistralrs_core::pipeline::loaders::Loader>::load_model_from_path
5: <mistralrs_core::pipeline::gguf::GGUFLoader as mistralrs_core::pipeline::loaders::Loader>::load_model_from_hf
6: mistralrs_server::main::{{closure}}
7: tokio::runtime::park::CachedParkThread::block_on
8: mistralrs_server::main

@franklucky001 franklucky001 added the new feature New feature or request label Oct 15, 2024
@EricLBuehler
Copy link
Owner

@franklucky001 #860 supports GGUF Qwen 2!

@franklucky001
Copy link
Author

@EricLBuehler Qwen2 define in master branch

pub enum GGUFArchitecture {
    Llama,
    Mpt,
    Gptneox,
    Gptj,
    Gpt2,
    Bloom,
    Falcon,
    Mamba,
    Rwkv,
    Phi2,
    Phi3,
    Starcoder2,
    Qwen2,
}

but not found in 0.3.1 https://github.com/EricLBuehler/mistral.rs/blob/v0.3.1/mistralrs-core/src/gguf/mod.rs

pub enum GGUFArchitecture {
    Llama,
    Mpt,
    Gptneox,
    Gptj,
    Gpt2,
    Bloom,
    Falcon,
    Mamba,
    Rwkv,
    Phi2,
    Phi3,
    Starcoder2,
}

Can you provide the docker image built from the master branch?

@EricLBuehler
Copy link
Owner

@franklucky001 v0.3.2 will be released soon, I'll let you know!

@franklucky001
Copy link
Author

@EricLBuehler that's great! thanks

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
new feature New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants