HuatuoGPT2-13B
Quick Start
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/HuatuoGPT2-13B", use_fast=True, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT2-13B", device_map="auto", torch_dtype='auto', trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("FreedomIntelligence/HuatuoGPT2-13B")
messages = []
messages.append({"role": "user", "content": "肚子疼怎么办?"})
response = model.HuatuoChat(tokenizer, messages)
print(response)
- Downloads last month
- 96
Inference API (serverless) does not yet support model repos that contain custom code.