Update app.py

app.py

@@ -14,77 +14,69 @@ import uuid
 
 
 MODEL_OPTIONS = [
-    "meta-llama/Llama-3.2-3B-Instruct",
-    "meta-llama/Llama-3.2-1B-Instruct",
-    "HuggingFaceH4/zephyr-7b-beta",
-    "meta-llama/Llama-3.1-8B",
-    "deepseek-ai/DeepSeek-R1",
-    "meta-llama/Llama-3-8B-Instruct",
-    "Qwen/Qwen3-8B",
-    "moonshotai/Kimi-K2-Tinking",
-    "openai/gpt-oss-20b",
-    "zai-org/GLM-4.6",
-    "moonshotai/Kimi-K2-Thinking",
-    "meta-llama/Llama-3.1-8B-Instruct",
     "allenai/Olmo-3-32B-Think",
     "allenai/Olmo-3-7B-Instruct",
-    "openai/gpt-oss-20b",
     "allenai/Olmo-3-7B-Think",
-    "zai-org/GLM-4.6",
-    "openai/gpt-oss-120b",
-    "MiniMaxAI/MiniMax-M2",
-    "meta-llama/Llama-3.2-3B-Instruct",
-    "Qwen/Qwen2.5-7B-Instruct",
-    "PrimeIntellect/INTELLECT-3-FP8",
+    "ArliAI/QwQ-32B-ArliAI-RpR-v4",
+    "baichuan-inc/Baichuan-M2-32B",
+    "darkc0de/XortronCriminalComputingConfig",
+    "deepseek-ai/DeepSeek-R1",
+    "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
+    "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+    "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+    "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+    "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+    "deepseek-ai/DeepSeek-V3.1-Terminus",
     "deepseek-ai/DeepSeek-V3.2-Exp",
-    "Qwen/Qwen3-4B-Instruct-2507",
+    "DeepHat/DeepHat-V1-7B",
     "dphn/Dolphin-Mistral-24B-Venice-Edition",
+    "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1",
+    "google/gemma-2-2b-it",
+    "Gryphe/MythoMax-L2-13b",
+    "HuggingFaceH4/zephyr-7b-beta",
+    "HuggingFaceTB/SmolLM3-3B",
+    "inclusionAI/Ling-1T",
+    "Intelligent-Internet/II-Medical-8B",
+    "meta-llama/Llama-3-8B-Instruct",
     "meta-llama/Llama-3.1-8B",
-    "Qwen/Qwen3-Next-80B-A3B-Instruct",
-    "deepseek-ai/DeepSeek-R1",
-    "Qwen/Qwen3-8B",
-    "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+    "meta-llama/Llama-3.1-8B-Instruct",
     "meta-llama/Llama-3.2-1B-Instruct",
-    "moonshotai/Kimi-K2-Instruct",
-    "nvidia/NVIDIA-Nemotron-Nano-12B-v2",
-    "meta-llama/Meta-Llama-3-8B-Instruct",
+    "meta-llama/Llama-3.2-3B-Instruct",
     "meta-llama/Llama-3.3-70B-Instruct",
-    "Qwen/Qwen3-32B",
-    "HuggingFaceTB/SmolLM3-3B",
-    "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
-    "zai-org/GLM-4.5-Air",
-    "Qwen/Qwen3-4B-Thinking-2507",
-    "moonshotai/Kimi-K2-Instruct-0905",
-    "Qwen/Qwen3-1.7B",
-    "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
-    "Qwen/Qwen3-235B-A22B-Instruct-2507",
-    "Qwen/Qwen3-30B-A3B-Instruct-2507",
-    "baichuan-inc/Baichuan-M2-32B",
-    "mistralai/Mistral-7B-Instruct-v0.2",
+    "meta-llama/Llama-Guard-3-8B",
     "meta-llama/Meta-Llama-3-8B",
+    "meta-llama/Meta-Llama-3-8B-Instruct",
+    "MiniMaxAI/MiniMax-M2",
+    "mistralai/Mistral-7B-Instruct-v0.2",
+    "moonshotai/Kimi-K2-Instruct",
+    "moonshotai/Kimi-K2-Instruct-0905",
+    "moonshotai/Kimi-K2-Thinking",
+    "moonshotai/Kimi-K2-Tinking",
+    "nvidia/NVIDIA-Nemotron-Nano-12B-v2",
+    "openai/gpt-oss-120b",
+    "openai/gpt-oss-20b",
+    "PrimeIntellect/INTELLECT-3-FP8",
     "Qwen/Qwen2.5-1.5B-Instruct",
-    "Qwen/Qwen3-Next-80B-A3B-Thinking",
-    "deepseek-ai/DeepSeek-V3.1-Terminus",
-    "HuggingFaceH4/zephyr-7b-beta",
-    "google/gemma-2-2b-it",
-    "meta-llama/Llama-Guard-3-8B",
-    "Qwen/Qwen2.5-Coder-7B-Instruct",
-    "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
-    "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1",
-    "darkc0de/XortronCriminalComputingConfig",
-    "ArliAI/QwQ-32B-ArliAI-RpR-v4",
-    "inclusionAI/Ling-1T",
-    "Gryphe/MythoMax-L2-13b",
     "Qwen/Qwen2.5-7B",
+    "Qwen/Qwen2.5-7B-Instruct",
     "Qwen/Qwen2.5-Coder-1.5B-Instruct",
-    "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
-    "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-    "DeepHat/DeepHat-V1-7B",
+    "Qwen/Qwen2.5-Coder-7B-Instruct",
+    "Qwen/Qwen3-1.7B",
     "Qwen/Qwen3-14B",
     "Qwen/Qwen3-30B-A3B",
-    "Intelligent-Internet/II-Medical-8B",
-    "zai-org/GLM-4.5",    
-    ]
+    "Qwen/Qwen3-30B-A3B-Instruct-2507",
+    "Qwen/Qwen3-32B",
+    "Qwen/Qwen3-4B-Instruct-2507",
+    "Qwen/Qwen3-4B-Thinking-2507",
+    "Qwen/Qwen3-8B",
+    "Qwen/Qwen3-235B-A22B-Instruct-2507",
+    "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+    "Qwen/Qwen3-Next-80B-A3B-Instruct",
+    "Qwen/Qwen3-Next-80B-A3B-Thinking",
+    "zai-org/GLM-4.5",
+    "zai-org/GLM-4.5-Air",
+    "zai-org/GLM-4.6",
+]
 
 
 # Suppress warnings
@@ -300,41 +292,36 @@ with gr.Blocks(title="QA Bot - PDF Question Answering") as demo:
                 truncate_slider = gr.Dropdown(
                     label="Embedding Model",
                     choices=[
-                        "sentence-transformers/all-MiniLM-L6-v2",
-                        "sentence-transformers/all-mpnet-base-v2",
-                        "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
-                        "BAAI/bge-small-en-v1.5",
+                        "ai-forever/ru-en-RoSBERTa",
                         "BAAI/bge-base-en-v1.5",
-                        "google/embeddinggemma-300m",
-                        "sentence-transformers/all-MiniLM-L6-v2",
+                        "BAAI/bge-base-zh-v1.5",
+                        "BAAI/bge-large-en-v1.5",
                         "BAAI/bge-m3",
-                        "Qwen/Qwen3-Embedding-8B",
-                        "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
-                        "MongoDB/mdbr-leaf-mt",
-                        "BAAI/bge-base-en-v1.5",
-                        "intfloat/multilingual-e5-large",
-                        "ai-forever/ru-en-RoSBERTa",
+                        "BAAI/bge-small-en-v1.5",
                         "cointegrated/rubert-tiny2",
-                        "jhgan/ko-sroberta-multitask",
-                        "sentence-transformers/all-mpnet-base-v2",
+                        "google/embeddinggemma-300m",
+                        "intfloat/multilingual-e5-base",
+                        "intfloat/multilingual-e5-large",
                         "intfloat/multilingual-e5-small",
+                        "jhgan/ko-sroberta-multitask",
+                        "lokeshch19/ModernPubMedBERT",
+                        "mixedbread-ai/mxbai-embed-large-v1",
                         "mixedbread-ai/mxbai-embed-xsmall-v1",
-                        "Snowflake/snowflake-arctic-embed-l-v2.0",
-                        "sentence-transformers/LaBSE",
+                        "MongoDB/mdbr-leaf-mt",
+                        "pritamdeka/S-Biomed-Roberta-snli-multinli-stsb",
+                        "pritamdeka/S-PubMedBert-MS-MARCO",
+                        "Qwen/Qwen3-Embedding-8B",
+                        "sentence-transformers/all-MiniLM-L6-v2",
                         "sentence-transformers/all-MiniLM-L12-v2",
+                        "sentence-transformers/all-mpnet-base-v2",
+                        "sentence-transformers/clip-ViT-B-32-multilingual-v1",
+                        "sentence-transformers/LaBSE",
+                        "sentence-transformers/msmarco-MiniLM-L6-v3",
+                        "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
                         "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
                         "shibing624/text2vec-base-chinese",
-                        "intfloat/multilingual-e5-base",
-                        "BAAI/bge-large-en-v1.5",
-                        "BAAI/bge-small-en-v1.5",
-                        "BAAI/bge-base-zh-v1.5",
-                        "mixedbread-ai/mxbai-embed-large-v1",
+                        "Snowflake/snowflake-arctic-embed-l-v2.0",
                         "Snowflake/snowflake-arctic-embed-m-v1.5",
-                        "lokeshch19/ModernPubMedBERT",
-                        "pritamdeka/S-Biomed-Roberta-snli-multinli-stsb",
-                        "pritamdeka/S-PubMedBert-MS-MARCO",
-                        "sentence-transformers/clip-ViT-B-32-multilingual-v1",
-                        "sentence-transformers/msmarco-MiniLM-L6-v3"
                     ],
                     value="sentence-transformers/all-MiniLM-L6-v2",
                     info="Model used for generating embeddings"
@@ -383,6 +370,16 @@ with gr.Blocks(title="QA Bot - PDF Question Answering") as demo:
     
     gr.Markdown(
         """
+        ### 📝 Instructions
+        1. Upload a PDF document
+        2. Enter your question in the text box
+        3. (Optional) Select a different LLM model
+        4. (Optional) Adjust advanced settings for fine-tuning
+        5. Click "Ask Question" to get an answer
+        
+        ### 🔐 Setup
+        This Space requires a HuggingFace API token. Set the following in your Space secrets:
+        - `HF_TOKEN`: Your HuggingFace API token (get it from https://huggingface.co/settings/tokens)
         """
     )