This model is suitable for role-playing and storytelling, but it's not a great model for multi-turn chat.
This was created for personal and academic use only. This merge model uses only fine-tune models of Llama2, but some of the models used include those whose licenses for commercial use are unclear.
If there is a license problem, the rights holder should contact me directly. No license changes will be made due to contact from others.
Test environment
This model was tested using text-generation-webui. I use preset simple-1 and Null preset for Generation.
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "nitky/Swallow-70b-RP"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="auto", load_in_4bit = True)
PROMPT_DICT = {
"prompt_input": (
"以下に、あるタスクを説明する指示があり、それに付随する入力が更なる文脈を提供しています。"
"リクエストを適切に完了するための回答を記述してください。\n\n"
"### 指示:\n{instruction}\n\n### 入力:\n{input}\n\n### 応答:"
),
"prompt_no_input": (
"以下に、あるタスクを説明する指示があります。"
"リクエストを適切に完了するための回答を記述してください。\n\n"
"### 指示:\n{instruction}\n\n### 応答:"
),
}
def create_prompt(instruction, input=None):
"""
Generates a prompt based on the given instruction and an optional input.
If input is provided, it uses the 'prompt_input' template from PROMPT_DICT.
If no input is provided, it uses the 'prompt_no_input' template.
Args:
instruction (str): The instruction describing the task.
input (str, optional): Additional input providing context for the task. Default is None.
Returns:
str: The generated prompt.
"""
if input:
# Use the 'prompt_input' template when additional input is provided
return PROMPT_DICT["prompt_input"].format(instruction=instruction, input=input)
else:
# Use the 'prompt_no_input' template when no additional input is provided
return PROMPT_DICT["prompt_no_input"].format(instruction=instruction)
# Example usage
instruction_example = "以下のトピックに関する詳細な情報を提供してください。"
input_example = "東京工業大学の主なキャンパスについて教えてください"
prompt = create_prompt(instruction_example, input_example)
input_ids = tokenizer.encode(
prompt,
add_special_tokens=False,
return_tensors="pt"
)
tokens = model.generate(
input_ids.to(device=model.device),
max_new_tokens=200,
temperature=0.7,
top_p=0.9,
repetition_penalty=1.15,
top_k=20,
do_sample=True,
)
out = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(out)