DougAnderson444/candle-qwen-2-5

Qwen2.5-Instruct in the Candle ML Framework, and a cli to use it

Rust

96 commits

updated May 28, 2026

See the code

README

Candle Machine Learning library Utilities

Project contains the crates:

Qwen 2.5 core model code
Qwen 2.5 cli
Basic Dioxus App
Vector Emeddings using Candle & Intfloat E5 small v2 model

Model cache from Hugging Face

The model files are cached from Hugging Face. You can find the model here. The cache directory is usually located at ~/.cache/huggingface/hub/models--Qwen--Qwen-2.5-Base/snapshots/<commit_hash>/.

Contributors

DougAnderson444

96 commits

Similar repos

alvanli/hubert

atomicstrata/candle

Private fork of huggingface/candle: adds Qwen3 KV snapshot/restore for am-local-slm prefix caching.…

Not-Buddy/FineTunnning

Me trying to train qwen base model with data that i have

raghavlite/B3_Qwen2_2B

Model

Model Card for Model ID

FanqingM/MM-Eureka-Qwen-7B

Model

More detailed can refer https://github.com/ModalMinds/MM-EUREKA

Osilly/Acital-Qwen-2.5VL-7B

Model

raghavlite/B3_Qwen2_7B

Model

Model Card for Model ID

kigichang/candle-notebook

學習 Huggingface Candle 筆記

Languages

Rust

99.4%

DougAnderson444/candle-qwen-2-5

Qwen2.5-Instruct in the Candle ML Framework, and a cli to use it

Rust

96 commits

updated May 28, 2026

See the code

README

Candle Machine Learning library Utilities

Project contains the crates:

Qwen 2.5 core model code
Qwen 2.5 cli
Basic Dioxus App
Vector Emeddings using Candle & Intfloat E5 small v2 model

Model cache from Hugging Face

The model files are cached from Hugging Face. You can find the model here. The cache directory is usually located at ~/.cache/huggingface/hub/models--Qwen--Qwen-2.5-Base/snapshots/<commit_hash>/.