Add application file

app.py

@@ -1,20 +1,47 @@
-from langchain.chat_models import ChatOpenAI
-from langchain.schema import AIMessage, HumanMessage
-import openai
-import os
 import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
 
-os.environ["OPENAI_API_KEY"] = "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"  # Replace with your key
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
+model = model.to('cuda:0')
 
-llm = ChatOpenAI(temperature=1.0, model='gpt-3.5-turbo-0613')
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [29, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
 
 def predict(message, history):
-    history_langchain_format = []
-    for human, ai in history:
-        history_langchain_format.append(HumanMessage(content=human))
-        history_langchain_format.append(AIMessage(content=ai))
-    history_langchain_format.append(HumanMessage(content=message))
-    gpt_response = llm(history_langchain_format)
-    return gpt_response.content
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
+                for item in history_transformer_format])
+
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        do_sample=True,
+        top_p=0.95,
+        top_k=1000,
+        temperature=1.0,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+        )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    partial_message = ""
+    for new_token in streamer:
+        if new_token != '<':
+            partial_message += new_token
+            yield partial_message
 
 gr.ChatInterface(predict).launch()