support autogptq in llama board #246

Former-commit-id: fea01226703d1534b5cf511bcb6a49e73bc86ce1

src/llmtuner/webui/components/data.py

@@ -21,8 +21,11 @@ def next_page(page_index: int, total_num: int) -> int:
 
 
 def can_preview(dataset_dir: str, dataset: list) -> Dict[str, Any]:
-    with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
-        dataset_info = json.load(f)
+    try:
+        with open(os.path.join(dataset_dir, DATA_CONFIG), "r", encoding="utf-8") as f:
+            dataset_info = json.load(f)
+    except:
+        return gr.update(interactive=False)
 
     if (
         len(dataset) > 0

src/llmtuner/webui/components/export.py

@@ -10,6 +10,9 @@ if TYPE_CHECKING:
     from llmtuner.webui.engine import Engine
 
 
+GPTQ_BITS = ["8", "4", "3", "2"]
+
+
 def save_model(
     lang: str,
     model_name: str,
@@ -18,6 +21,8 @@ def save_model(
     finetuning_type: str,
     template: str,
     max_shard_size: int,
+    export_quantization_bit: int,
+    export_quantization_dataset: str,
     export_dir: str
 ) -> Generator[str, None, None]:
     error = ""
@@ -25,23 +30,32 @@ def save_model(
         error = ALERTS["err_no_model"][lang]
     elif not model_path:
         error = ALERTS["err_no_path"][lang]
-    elif not adapter_path:
-        error = ALERTS["err_no_adapter"][lang]
     elif not export_dir:
         error = ALERTS["err_no_export_dir"][lang]
+    elif export_quantization_bit in GPTQ_BITS and not export_quantization_dataset:
+        error = ALERTS["err_no_dataset"][lang]
+    elif export_quantization_bit not in GPTQ_BITS and not adapter_path:
+        error = ALERTS["err_no_adapter"][lang]
 
     if error:
         gr.Warning(error)
         yield error
         return
 
+    if adapter_path:
+        adapter_name_or_path = ",".join([get_save_dir(model_name, finetuning_type, adapter) for adapter in adapter_path])
+    else:
+        adapter_name_or_path = None
+
     args = dict(
         model_name_or_path=model_path,
-        adapter_name_or_path=",".join([get_save_dir(model_name, finetuning_type, adapter) for adapter in adapter_path]),
+        adapter_name_or_path=adapter_name_or_path,
         finetuning_type=finetuning_type,
         template=template,
         export_dir=export_dir,
-        export_size=max_shard_size
+        export_size=max_shard_size,
+        export_quantization_bit=int(export_quantization_bit) if export_quantization_bit in GPTQ_BITS else None,
+        export_quantization_dataset=export_quantization_dataset
     )
 
     yield ALERTS["info_exporting"][lang]
@@ -51,9 +65,11 @@ def save_model(
 
 def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
     with gr.Row():
-        export_dir = gr.Textbox()
         max_shard_size = gr.Slider(value=1, minimum=1, maximum=100)
+        export_quantization_bit = gr.Dropdown(choices=["none", "8", "4", "3", "2"], value="none")
+        export_quantization_dataset = gr.Textbox(value="data/c4_demo.json")
 
+    export_dir = gr.Textbox()
     export_btn = gr.Button()
     info_box = gr.Textbox(show_label=False, interactive=False)
 
@@ -67,14 +83,18 @@ def create_export_tab(engine: "Engine") -> Dict[str, "Component"]:
             engine.manager.get_elem_by_name("top.finetuning_type"),
             engine.manager.get_elem_by_name("top.template"),
             max_shard_size,
+            export_quantization_bit,
+            export_quantization_dataset,
             export_dir
         ],
         [info_box]
     )
 
     return dict(
-        export_dir=export_dir,
         max_shard_size=max_shard_size,
+        export_quantization_bit=export_quantization_bit,
+        export_quantization_dataset=export_quantization_dataset,
+        export_dir=export_dir,
         export_btn=export_btn,
         info_box=info_box
     )

src/llmtuner/webui/components/top.py

@@ -20,7 +20,7 @@ def create_top() -> Dict[str, "Component"]:
 
     with gr.Row():
         finetuning_type = gr.Dropdown(choices=METHODS, value="lora", scale=1)
-        adapter_path = gr.Dropdown(multiselect=True, scale=5)
+        adapter_path = gr.Dropdown(multiselect=True, scale=5, allow_custom_value=True)
         refresh_btn = gr.Button(scale=1)
 
     with gr.Accordion(label="Advanced config", open=False) as advanced_tab:

src/llmtuner/webui/components/train.py

@@ -94,7 +94,7 @@ def create_train_tab(engine: "Engine") -> Dict[str, "Component"]:
     with gr.Accordion(label="RLHF config", open=False) as rlhf_tab:
         with gr.Row():
             dpo_beta = gr.Slider(value=0.1, minimum=0, maximum=1, step=0.01, scale=1)
-            reward_model = gr.Dropdown(scale=3)
+            reward_model = gr.Dropdown(scale=3, allow_custom_value=True)
             refresh_btn = gr.Button(scale=1)
 
     refresh_btn.click(