ポンコツです。

system prompt:

私はアシスタントチャットボットとしてユーザーの命令に従います。
<think>ここで慎重に考える</think><answer>答え</answer> のように、<think></think><answer></answer> の形式で思考過程とファイナルアンサーを回答します。

example:

import torch
from transformers import pipeline, AutoTokenizer

messages = [
    {"role": "system"},
# # optional one-shot:
#    {
#        "role": "user",
#        "content": """
#次の問題を解き、計算結果を数値のみで答えてください。
#10 * (23 + 45) - 67 = ?
#""".strip(),
#    },
#    {
#        "role": "assistant",
#        "content": """
#<think>
#与えられた式には括弧が含まれるため、先に括弧内の計算を行う必要があります。
#23 + 45 = 68 なので、等式は以下のように変形できます。
#10 * (23 + 45) - 67 = 10 * 68 - 67
#四則演算の優先順位に従い、掛け算を行ったのちに引き算を行います。
#10 * 68 - 67 = 680 - 67 = 613
#従って、計算結果は 613 です。数値のみを回答すべきなので、613 を回答します。
#</think>
#<answer>613</answer>
#""".strip(),
#    },
    {
        "role": "user",
        "content": "ブレナンは学校の課題のために研究をしており、参考にするためにインターネットからファイルをコンピュータにダウンロードする必要がありました。800個のファイルをダウンロードした後、役に立たないものを70%削除しました。さらに400個のファイルをダウンロードしましたが、再び3/5が関係ないことに気づきました。2回目にダウンロードした関係のないファイルを削除した後、彼は何個の価値のあるファイルを持っていましたか?",
    },
]

pipe = pipeline(
    "text-generation",
    model="p1atdev/llm-jp-3-3.7b-R26",
    torch_dtype=torch.bfloat16,
    use_cache=True,
)

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
print(prompt)
print("↓↓↓補完")
output = pipe(
    prompt,
    do_sample=True,
    max_new_tokens=256,
    temperature=0.8,
    repetition_penalty=1.0,
)[0]["generated_text"][len(prompt) :].strip()
print(output)
Downloads last month
39
Safetensors
Model size
3.78B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for p1atdev/llm-jp-3-3.7b-R26

Finetuned
(7)
this model

Dataset used to train p1atdev/llm-jp-3-3.7b-R26