Deploy Finance QnA AI\

README.md

@@ -1,13 +1,3 @@
 ---
-title: LLM Finance QnA Test
-emoji: 📈
-colorFrom: purple
-colorTo: purple
-sdk: gradio
-sdk_version: 5.20.1
-app_file: app.py
-pinned: false
 license: mit
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load base model & tokenizer
+base_model = "vilsonrodrigues/falcon-7b-instruct-sharded"
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16, device_map="auto")
+
+# Load LoRA adapter
+adapter_path = "./model"
+model = PeftModel.from_pretrained(model, adapter_path)
+
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_length=200)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(label="Masukkan pertanyaan finansial"),
+    outputs=gr.Textbox(label="Jawaban AI"),
+    title="Financial AI Chatbot",
+    description="Fine-tuned Falcon 7B Model untuk QnA Finansial."
+)
+
+if __name__ == "__main__":
+    interface.launch()

model/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00aff546715ff8f3831c1fdf2c8556ed57db905470bb3b8099f7f15a18aed51
+size 18883912

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+transformers
+torch
+peft
+accelerate
+huggingface_hub
+