cognitivecomputations

/

dolphincoder-starcoder2-7b

like 9

I've loaded this using a basic gradio interface .. however when I ask it anything, it is a stream of markup language that just goes on indefinitely. How do i change it to the ChatML prompt format? (I'm just learning)

Here's the code I lifted from gradio:

import gradio as gr
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
from threading import Thread

tokenizer = AutoTokenizer.from_pretrained("cognitivecomputations/dolphincoder-starcoder2-7b")
model = AutoModelForCausalLM.from_pretrained("cognitivecomputations/dolphincoder-starcoder2-7b", torch_dtype=torch.float16)
model = model.to('cuda:0')

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_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).queue()
gr.ChatInterface(predict).launch()