MyModel-pretrain / README.md
HappyBulingling's picture
Upload MyModel checkpoint
9b53d42 verified
|
Raw History Blame Contribute Delete
835 Bytes
metadata
library_name: transformers
pipeline_tag: text-generation
tags:
  - mymodel
  - causal-lm

MyModel-pretrain

MyModel 稠密文本模型(decay-4k),参数量 259M,训练 step 22,889,tokens 6.00B。

使用

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "HappyBulingling/MyModel-pretrain"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)

messages = [{"role": "user", "content": "你好"}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt", enable_thinking=True
)
outputs = model.generate(
    inputs, max_new_tokens=256, do_sample=True, temperature=0.8, top_p=0.9
)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))