Downloads · 30 days
15
22% of all-time downloads
OpenSakura/OpenSakura-MODEL-260508-LN-ja-zh-SFT-qwen36-35b-a3b-sft-SHIT
OpenSakura-MODEL-260508-LN-ja-zh-SFT-qwen36-35b-a3b-sft-SHIT is a translation model from OpenSakura. Use it when you need text moved from one language to another. It is set up for transformers.
This model was trained with a garbage dataset that can drop sentences during translation. Do not use this model for production, evaluation, release, or any downstream work until the OpenSakura team has properly organi…
Downloads · 30 days
15
22% of all-time downloads
All-time downloads
68
Public
Parameters
34.7B
69.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors69.3 GB · 100%
From the Hugging Face model README
This model was trained with a garbage dataset that can drop sentences during translation. Do not use this model for production, evaluation, release, or any downstream work until the OpenSakura team has properly organized and retried the dataset generation process and retrained the model.
Known issue: translations may omit input sentences even though the training prompt explicitly asks for one output line per input line.
/tmp/scratch-space/runs/260513/outputs/checkpoint-5000OpenSakura/OpenSakura-MODEL-260419-LN-ja-zh-PT-qwen36-35b-a3b-cpt543c3f95d2c08b43e3afcd1232e9b2859c0b264bmain_lilith65_eve350.65, Eve 0.35native_qwen_thinkingnative_qwen_empty_thinkingbfloat16The formatter builds a normal Qwen chat conversation with a system message and
a user message, then starts the assistant with Qwen native thinking tags.
你是专业的日文轻小说中文译者。请将输入的日文原文翻译为流畅、自然、具有轻小说/二次元语感的简体中文。
要求:
1. 严格保持行数一一对应:输入多少行,输出多少行,不合并、不拆分、不遗漏。
2. 根据上下文自然补全日文省略的主语,并保持角色口吻、性格、性别感和对话关系。
3. 保留原文的特殊格式,包括行首全角空格、转义符、特殊符号等。
4. Ruby/注音格式如“漢字(よみ)”若承载双关、设定、特殊称呼或魔法名,应在译文中保留“汉字(注音)”结构;普通读音标注则直接翻译含义。
5. 日文标点转换为中文标点,如「」转为“”,、转为,。
6. 忠实翻译原文的语气、粗俗度、暴力感、暧昧感和文学风格,不擅自删减、净化、美化或解释。
只输出译文纯文本,不输出说明、分析、JSON、开场白或结束语。
输入(总行数: {line_count}):
{source_text}
When glossary entries are present, the formatter prepends them before the input block:
术语表 <术语原文> -> <术语译文> #<术语信息>:
{source_term_1} -> {target_term_1} #{info_1}
{source_term_2} -> {target_term_2} #{info_2}
输入(总行数: {line_count}):
{source_text}
The tokenizer chat template renders the prompt as Qwen chat markers:
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{user_prompt}<|im_end|>
<|im_start|>assistant
<think>
For Eve empty-thinking examples, the assistant prefill is:
<think>
</think>
{final_translation}<|im_end|>
For Lilith thinking examples, the assistant target is:
<think>
{reasoning_content}
</think>
{final_translation}<|im_end|>
This illustrates the training prompt shape only. The model is not recommended for use.
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": "输入(总行数: 1):\nこれは例ではありません。",
},
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True,
)
Note: the training user prompt header is Chinese 输入(总行数: N):.
This checkpoint is published only as an internal artifact. It should be replaced after the dataset-generation pipeline is fixed, the data is regenerated, and the model is retrained.