glm0620 是基于glm4-9B-Chat模型、用英雄之冠玩家交流群的聊天记录作为数据集训练得到的模型。该模型用以模拟英雄之冠玩家，与用户进行对话
您可以通过如下git clone命令，或者ModelScope SDK来下载模型
SDK下载
#安装ModelScope
pip install modelscope
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('heruohai/glm0620',cache_dir='指定下载目录')
Git下载
#Git模型下载
git clone https://www.modelscope.cn/heruohai/glm0620.git
下载后请与网页端的文件列表进行对比，检查是否有文件遗漏。若有遗漏可以通过手动下载
模型下载后可通过huggingface进行推理
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model_path = "下载好的模型所在目录"
tokenizer = AutoTokenizer.from_pretrained(model_path,trust_remote_code=True)
query = "你好"
inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
add_generation_prompt=True,
tokenize=True,
return_tensors="pt",
return_dict=True
)
inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
model_path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True
).to(device).eval()
gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
outputs = model.generate(**inputs, **gen_kwargs)
outputs = outputs[:, inputs['input_ids'].shape[1]:]
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
多轮对话demo
import os
import torch
from threading import Thread
from transformers import AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer, AutoModel
MODEL_PATH = "heruohai/glm0620" #修改为本地的模型目录
tokenizer = AutoTokenizer.from_pretrained(
MODEL_PATH,
trust_remote_code=True,
encode_special_tokens=True
)
model = AutoModel.from_pretrained(
MODEL_PATH,
trust_remote_code=True,
device_map="auto").eval()
class StopOnTokens(StoppingCriteria):
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
stop_ids = model.config.eos_token_id
for stop_id in stop_ids:
if input_ids[0][-1] == stop_id:
return True
return False
if __name__ == "__main__":
history = []
max_length = 8192
top_p = 0.8
temperature = 0.6
stop = StopOnTokens()
print("Welcome to the GLM-4-9B CLI chat. Type your messages below.")
while True:
user_input = input("\nYou: ")
if user_input.lower() in ["exit", "quit"]:
break
history.append([user_input, ""])
messages = []
for idx, (user_msg, model_msg) in enumerate(history):
if idx == len(history) - 1 and not model_msg:
messages.append({"role": "user", "content": user_msg})
break
if user_msg:
messages.append({"role": "user", "content": user_msg})
if model_msg:
messages.append({"role": "assistant", "content": model_msg})
model_inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_tensors="pt"
).to(model.device)
streamer = TextIteratorStreamer(
tokenizer=tokenizer,
timeout=60,
skip_prompt=True,
skip_special_tokens=True
)
generate_kwargs = {
"input_ids": model_inputs,
"streamer": streamer,
"max_new_tokens": max_length,
"do_sample": True,
"top_p": top_p,
"temperature": temperature,
"stopping_criteria": StoppingCriteriaList([stop]),
"repetition_penalty": 1.2,
"eos_token_id": model.config.eos_token_id,
}
t = Thread(target=model.generate, kwargs=generate_kwargs)
t.start()
print("GLM-4:", end="", flush=True)
for new_token in streamer:
if new_token:
print(new_token, end="", flush=True)
history[-1][1] += new_token
history[-1][1] = history[-1][1].strip()
如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。
评论