SSR-Zero-7B

Github: https://github.com/Kelaxon/SSR-Zero

Quickstart

Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "wjyccs/SSR-Zero-7B"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)


system_prompt = """<|startoftext|>A conversation between User and Assistant. The User asks a question, and the Assistant solves it. \
The Assistant first thinks about the reasoning process in the mind and then provides the User with the answer. \
The reasoning process is enclosed within <think> </think> and answer is enclosed within <answer> </answer> tags, respectively, \
i.e., <think> reasoning process here </think> <answer> answer here </answer>. \

User:
{}

Assistant:
"""

# For English to Chinese translation, use:
instruction = "Translate the following text to Chinese: \n{}"
# For Chinese to English translation, use:
# instruction = "Translate the following text to English: \n{}"

src_text = "Plants make oxygen which humans breathe, and they take in carbon-dioxide which humans exhale (that is, breathe out)."
prompt = system_prompt.format(instruction.format(src_text))

messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)