Update app.py

app.py

@@ -1,3 +1,43 @@
-import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-gr.load("models/cognitivecomputations/dolphin-2.6-mixtral-8x7b").launch()
+model_name_or_path = "TheBloke/dolphin-2.5-mixtral-8x7b-GPTQ"
+# To use a different branch, change revision
+# For example: revision="gptq-4bit-128g-actorder_True"
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
+                                             device_map="auto",
+                                             trust_remote_code=False,
+                                             revision="main")
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+
+prompt = "Write a story about llamas"
+system_message = "You are a story writing assistant"
+prompt_template=f'''<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+'''
+
+print("\n\n*** Generate:")
+
+input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
+output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
+print(tokenizer.decode(output[0]))
+
+# Inference can also be done using transformers' pipeline
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    repetition_penalty=1.1
+)
+
+print(pipe(prompt_template)[0]['generated_text'])