From 24ae0066ed8d0168734160a9cf8a475b794835f6 Mon Sep 17 00:00:00 2001
From: BuildTools <chenxuzhang45@gmail.com>
Date: Wed, 4 Sep 2024 17:31:39 -0700
Subject: [PATCH] feat: support key shortcuts for AutoFP8 window

- update README.md for v1.8.1
- remove aliased quant types
- update .env.example with all configuration parameters
---
 .env.example    |  3 +++
 README.md       | 16 ++++++++++------
 src/AutoGGUF.py |  4 +---
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/.env.example b/.env.example
index da700ce..5b89a1f 100644
--- a/.env.example
+++ b/.env.example
@@ -6,3 +6,6 @@ AUTOGGUF_SERVER_API_KEY=
 AUTOGGUF_MODEL_DIR_NAME=models
 AUTOGGUF_OUTPUT_DIR_NAME=quantized_models
 AUTOGGUF_RESIZE_FACTOR=1.1
+AUTOGGUF_SERVER=enabled
+AUTOGGUF_SERVER_PORT=7001
+AUTOGGUF_SERVER_API_KEY=
diff --git a/README.md b/README.md
index 70d6c82..6ceae44 100644
--- a/README.md
+++ b/README.md
@@ -35,6 +35,7 @@ AutoGGUF provides a graphical user interface for quantizing GGUF models using th
 - Parallel quantization + imatrix generation
 - LoRA conversion and merging
 - Preset saving and loading
+- AutoFP8 quantization
 
 ## Usage
 
@@ -49,6 +50,8 @@ AutoGGUF provides a graphical user interface for quantizing GGUF models using th
    ```
    or use the `run.bat` script.
 
+macOS and Ubuntu builds are provided with GitHub Actions, you may download the binaries in the releases section.
+
 ### Windows
 Standard builds:
 1. Download the latest release
@@ -62,6 +65,8 @@ Setup builds:
 4. The .GGUF extension will be registered with the program automatically
 5. Run the program from the Start Menu or desktop shortcuts
 
+After launching the program, you may access its local server at port 7001 (set `AUTOGGUF_SERVER` to "enabled" first)
+
 ### Verifying Releases
 
 #### Linux/macOS:
@@ -77,11 +82,11 @@ sha256sum -c AutoGGUF-v1.5.0-prerel.sha256
 gpg --import AutoGGUF-v1.5.0-prerel.asc
 
 # Verify the signature
-gpg --verify AutoGGUF-v1.5.0-Windows-avx2-prerel.zip.sig AutoGGUF-v1.5.0-Windows-avx2-prerel.zip
+gpg --verify AutoGGUF-v1.8.1-Windows-avx2.zip.sig AutoGGUF-v1.8.1-Windows-avx2.zip
 
 # Check SHA256
-$fileHash = (Get-FileHash -Algorithm SHA256 AutoGGUF-v1.5.0-Windows-avx2-prerel.zip).Hash.ToLower()
-$storedHash = (Get-Content AutoGGUF-v1.5.0-prerel.sha256 | Select-String AutoGGUF-v1.5.0-Windows-avx2-prerel.zip).Line.Split()[0]
+$fileHash = (Get-FileHash -Algorithm SHA256 AutoGGUF-v1.8.1-Windows-avx2.zip).Hash.ToLower()
+$storedHash = (Get-Content AutoGGUF-v1.8.1.sha256 | Select-String AutoGGUF-v1.8.1-Windows-avx2.zip).Line.Split()[0]
 if ($fileHash -eq $storedHash) { "SHA256 Match" } else { "SHA256 Mismatch" }
 ```
 
@@ -118,7 +123,7 @@ View the list of supported languages at [AutoGGUF/wiki/Installation#configuratio
 
 To use a specific language, set the `AUTOGGUF_LANGUAGE` environment variable to one of the listed language codes (note: some languages may not be fully supported yet, those will fall back to English).
 
-## Known Issues
+## Issues
 
 - None!
 
@@ -127,9 +132,8 @@ To use a specific language, set the `AUTOGGUF_LANGUAGE` environment variable to
 - Time estimation for quantization
 - Actual progress bar tracking 
 - Perplexity testing
-- Web API and management (partially implemented in v1.6.2)
 - HuggingFace upload/download (coming in the next release)
-- AutoFP8 quantization and bitsandbytes (coming in the next release)
+- AutoFP8 quantization (partially done) and bitsandbytes (coming soon)
 
 ## Troubleshooting
 
diff --git a/src/AutoGGUF.py b/src/AutoGGUF.py
index e7ce8f4..af93d3f 100644
--- a/src/AutoGGUF.py
+++ b/src/AutoGGUF.py
@@ -153,6 +153,7 @@ def __init__(self, args: List[str]) -> None:
         # Tools menu
         tools_menu = self.menubar.addMenu("&Tools")
         autofp8_action = QAction("&AutoFP8", self)
+        autofp8_action.setShortcut(QKeySequence("Shift+Q"))
         autofp8_action.triggered.connect(self.show_autofp8_window)
         tools_menu.addAction(autofp8_action)
 
@@ -321,17 +322,14 @@ def __init__(self, args: List[str]) -> None:
             "IQ3_XXS",
             "IQ3_S",
             "IQ3_M",
-            "Q3_K",
             "IQ3_XS",
             "Q3_K_S",
             "Q3_K_M",
             "Q3_K_L",
             "IQ4_NL",
             "IQ4_XS",
-            "Q4_K",
             "Q4_K_S",
             "Q4_K_M",
-            "Q5_K",
             "Q5_K_S",
             "Q5_K_M",
             "Q6_K",