version： 0.9.2-alpha.1
model： https://huggingface.co/unsloth/embeddinggemma-300m-GGUF
model file: embeddinggemma-300M-Q8_0.gguf

my code:
`
use candle_core::{IndexOp, Tensor, quantized::gguf_file};
use candle_transformers::models::quantized_gemma3::ModelWeights;

let mut file = std::fs::File::open(&model_file)?;
let model_content = gguf_file::Content::read(&mut file).map_err(|e| e.with_path(model_path))?;
let model = ModelWeights::from_gguf(model_content, &mut file, &device)?;
`
error:
cannot find gemma3.attention.head_count in metadata

check ModelWeights::from_gguf source code:

impl ModelWeights {
    pub fn from_gguf<R: std::io::Seek + std::io::Read>(
        ct: gguf_file::Content,
        reader: &mut R,
        device: &Device,
    ) -> Result<Self> {
        let md_get = |s: &str| match ct.metadata.get(s) {
            None => candle::bail!("**cannot find {s} in metadata**"),
            Some(v) => Ok(v),
        };

but, I use candle_transformers::models::quantized_qwen3 is fine,

quantized_qwen3::ModelWeights::from_gguf source code:

impl ModelWeights {
    pub fn from_gguf<R: Read + Seek>(
        ct: gguf_file::Content,
        reader: &mut R,
        device: &Device,
    ) -> Result<Self> {
        let mut gg = Gguf::new(ct, reader, device.clone());
        let md_get = |s: &str| match gg.metadata().get(s) {
            None => candle::bail!("cannot find {s} in metadata"),
            Some(v) => Ok(v),
        };

Should quantized_gemma3::ModelWeights::from_gguf be changed to add this line let mut gg = Gguf::new(ct, reader, device.clone()); ?