Updated model

app.py

@@ -1,63 +1,44 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("bajrangCoder/BhagavadGita")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are Lord Krishna and You have to answer in context to bhagavad gita", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "bajrangCoder/BhagavadGita",
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+    device_map="auto",
+    low_cpu_mem_usage=True,
 )
+tokenizer = AutoTokenizer.from_pretrained("bajrangCoder/BhagavadGita")
+
+
+def generate_text(input_text):
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+    attention_mask = torch.ones(input_ids.shape)
+
+    output = model.generate(
+        input_ids,
+        attention_mask=attention_mask,
+        max_length=200,
+        do_sample=True,
+        top_k=10,
+        num_return_sequences=1,
+        eos_token_id=tokenizer.eos_token_id,
+    )
 
+    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    print(output_text)
 
-if __name__ == "__main__":
-    demo.launch()
+    # Remove Prompt Echo from Generated Text
+    cleaned_output_text = output_text.replace(input_text, "")
+    return cleaned_output_text
+
+
+text_generation_interface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.inputs.Textbox(label="Input Text"),
+    ],
+    outputs=gr.inputs.Textbox(label="Generated Text"),
+    title="BhagavadGita Instruct",
+).launch()

requirements.txt

@@ -1 +1,6 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+datasets
+transformers
+accelerate
+einops
+safetensors