# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Bin12345/AutoCoder_QW_7B")
model = AutoModelForCausalLM.from_pretrained("Bin12345/AutoCoder_QW_7B")
messages = [
{"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))Quick Links
The base model of AutoCode_QW_7B is CodeQwen1.5-7b.
In this version, we fixed the problem that the model will only start the code interpreter when you ask it to verify its code.
you can try the code interpreter function on the AutoCoder GitHub
For the simple code generation without code interpreter ability, try the following script:
from transformers import AutoTokenizer, AutoModelForCausalLM
from datasets import load_dataset
model_path = "Bin12345/AutoCoder_QW_7B"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path,
device_map="auto")
Input = "" # input your question here
messages=[
{ 'role': 'user', 'content': Input}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True,
return_tensors="pt").to(model.device)
outputs = model.generate(inputs,
max_new_tokens=1024,
do_sample=False,
temperature=0.0,
top_p=1.0,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id)
answer = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Bin12345/AutoCoder_QW_7B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)