T5 Wasm (#918)

* init t5 wasm model

* split workers for each model

* clean up

* add some ui

* readme

* index

* typo

* remove cache param, clear_kv_cache

* add max_length as param

* add model tasks option to ui

* add method to load quantized gguf from buffer

* Add quantized wasm module

* add quantized models to UI, dynamic import wasms

* link to quantized

* fix copy

* fix ModelEncoder

* fix README.md

candle-transformers/src/models/quantized_t5.rs

@@ -30,6 +30,21 @@ impl VarBuilder {
         })
     }
 
+    pub fn from_gguf_buffer(buffer: &[u8]) -> Result<Self> {
+        let mut cursor = std::io::Cursor::new(buffer);
+        let content = candle::quantized::gguf_file::Content::read(&mut cursor)?;
+        let mut data = std::collections::HashMap::new();
+        for tensor_name in content.tensor_infos.keys() {
+            let tensor = content.tensor(&mut cursor, tensor_name)?;
+            data.insert(tensor_name.to_string(), Arc::new(tensor));
+        }
+        Ok(Self {
+            data: Arc::new(data),
+            path: Vec::new(),
+            device: Device::Cpu,
+        })
+    }
+
     fn pp<S: ToString>(&self, s: S) -> Self {
         let mut path = self.path.clone();
         path.push(s.to_string());