Bump version to v0.4.4

Cargo.toml

@@ -11,7 +11,7 @@ license = "MIT OR Apache-2.0"
 name = "ai00_server"
 repository = "https://github.com/cgisky1980/ai00_rwkv_server"
 rust-version = "1.75"
-version = "0.4.3"
+version = "0.4.4"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 

assets/configs/Config.toml

@@ -1,14 +1,14 @@
 [model]
 embed_device = "Cpu"                                       # Device to put the embed tensor ("Cpu" or "Gpu").
 max_batch = 8                                              # The maximum batches that are cached on GPU.
-model_path = "assets/models"                               # Path to the folder containing all models.
 model_name = "RWKV-x060-World-3B-v2.1-20240417-ctx4096.st" # Name of the model.
+model_path = "assets/models"                               # Path to the folder containing all models.
 quant = 0                                                  # Layers to be quantized.
 quant_type = "Int8"                                        # Quantization type ("Int8" or "NF4").
 stop = ["\n\n"]                                            # Additional stop words in generation.
 token_chunk_size = 128                                     # Size of token chunk that is inferred at once. For high end GPUs, this could be 64 or 128 (faster).
 
-# [state] # Initial state goes here
+# [state] # Initial state goes here.
 # path = "rwkv-x060-chn_single_round_qa-3B-20240502-ctx1024.st"
 
 [tokenizer]

src/api/model.rs

@@ -62,8 +62,8 @@ pub async fn load(depot: &mut Depot, req: &mut Request) -> StatusCode {
             Err(_) => return StatusCode::NOT_FOUND,
         }
     }
-    if let Some(s) = request.state.as_mut() {
-        s.path = match build_path(model_path, &s.path) {
+    if let Some(_state) = request.state.as_mut() {
+        _state.path = match build_path(model_path, &_state.path) {
             Ok(path) => path,
             Err(_) => return StatusCode::NOT_FOUND,
         }