kdf/jiang-chat

Model Card for Model ID

This modelcard aims to be a base template for new models. It has been generated using this raw template.

Model Details

Model Description

• Developed by: 知未智能KDF
• Model type: JIANG
• Language(s) (NLP): Chinese
• License: Reasearch only (because using other Reasearch-Only SFT datasets)
• Finetuned from model [optional]: https://huggingface.co/kdf/jiang-base

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'kdf/jiang-chat'
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
ret = model.generate(**tokenizer('<|unused52|>写首诗<|unused53|><|unused54|>', return_tensors='pt'), max_new_tokens=50, top_k=1)
print(tokenizer.decode(ret[0]))