import gradio as gr import gc, copy, re import urllib.request from rwkv.model import RWKV from rwkv.utils import PIPELINE, PIPELINE_ARGS ctx_limit = 4096 title = "RWKV-5-World-0.1B-v1-20230803-ctx4096.pth" url = f"https://huggingface.co/BlinkDL/rwkv-5-world/resolve/main/{title}" urllib.request.urlretrieve(url, title) model = RWKV(model=title, strategy='cpu bf16') pipeline = PIPELINE(model, "rwkv_vocab_v20230424") def generate_prompt(instruction, input=None, history=None): # parse the chat history into a string of user and assistant messages history_str = "" for pair in history: history_str += f"Instruction: {pair[0]}\n\nAssistant: {pair[1]}\n\n" instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n').replace('\n\n','\n') input = input.strip().replace('\r\n','\n').replace('\n\n','\n').replace('\n\n','\n') if input and len(input) > 0: return f"""{history_str}Instruction: {instruction} Input: {input} Response:""" else: return f"""{history_str}User: {instruction} Assistant:""" examples = [ ["東京で訪れるべき素晴らしい場所とその紹介をいくつか挙げてください。", "", 300, 1.2, 0.5, 0.5, 0.5], ["Écrivez un programme Python pour miner 1 Bitcoin, avec des commentaires.", "", 300, 1.2, 0.5, 0.5, 0.5], ["Write a song about ravens.", "", 300, 1.2, 0.5, 0.5, 0.5], ["Explain the following metaphor: Life is like cats.", "", 300, 1.2, 0.5, 0.5, 0.5], ["Write a story using the following information", "A man named Alex chops a tree down", 300, 1.2, 0.5, 0.5, 0.5], ["Generate a list of adjectives that describe a person as brave.", "", 300, 1.2, 0.5, 0.5, 0.5], ["You have $100, and your goal is to turn that into as much money as possible with AI and Machine Learning. Please respond with detailed plan.", "", 300, 1.2, 0.5, 0.5, 0.5], ] def evaluate( instruction, input=None, token_count=333, temperature=1.0, top_p=0.5, presencePenalty = 0.5, countPenalty = 0.5, history=None # add the history parameter to the evaluate function ): args = PIPELINE_ARGS(temperature = max(0.2, float(temperature)), top_p = float(top_p), alpha_frequency = countPenalty, alpha_presence = presencePenalty, token_ban = [], # ban the generation of some tokens token_stop = [0]) # stop generation whenever you see any token here instruction = re.sub(r'\n{2,}', '\n', instruction).strip().replace('\r\n','\n') input = re.sub(r'\n{2,}', '\n', input).strip().replace('\r\n','\n') ctx = generate_prompt(instruction, input, history) # pass the history to the generate_prompt function print(ctx + "\n") all_tokens = [] out_last = 0 out_str = '' occurrence = {} state = None for i in range(int(token_count)): out, state = model.forward(pipeline.encode(ctx)[-ctx_limit:] if i == 0 else [token], state) for n in occurrence: out[n] -= (args.alpha_presence + occurrence[n] * args.alpha_frequency) token = pipeline.sample_logits(out, temperature=args.temperature, top_p=args.top_p) if token in args.token_stop: break all_tokens += [token] for xxx in occurrence: occurrence[xxx] *= 0.996 if token not in occurrence: occurrence[token] = 1 else: occurrence[token] += 1 tmp = pipeline.decode(all_tokens[out_last:]) if '\ufffd' not in tmp: out_str += tmp yield out_str.strip() out_last = i + 1 if '\n\n' in out_str: break del out del state gc.collect() yield out_str.strip() def user(message, chatbot): chatbot = chatbot or [] return "", chatbot + [[message, None]] def alternative(chatbot, history): if not chatbot or not history: return chatbot, history chatbot[-1][1] = None history[0] = copy.deepcopy(history[1]) return chatbot, history with gr.Blocks(title=title) as demo: gr.HTML(f"