Views
No views yet
| 项目 | 值 |
|---|---|
| 基座 | Qwen/Qwen3-1.7B |
| 方法 | QLoRA 4-bit NF4 (双重量化), bf16 |
| LoRA | r=32, alpha=64, target: q/k/v/o/gate/up/down proj |
| 数据 | 1,233 条合成 SFT 对话 (MiMo-V2.5-Pro, 纯原文无情绪变体) |
| 训练 | 1 epoch, seed=478 |
| 格式 | Merged bf16 safetensors + GGUF F16 |
| 模型 | LoRA | 方法 | 版本 |
|---|---|---|---|
| Qwen3-1.7B-Yukari-SFT | r=8, a=8 | SFT | v1 |
| Qwen3-1.7B-Yukari-SFT-v2 (本模型) | r=32, a=64 | SFT | v2 |
| Qwen3-1.7B-Yukari-DPO | r=32, a=64 | SFT+DPO | v2+DPO |
[情绪标签]\n用户输入，标签控制八云紫的回复语气。8 维 Plutchik 情绪向量离散化：喜悦/愤怒/悲伤/恐惧/厌恶/惊讶/信任/期待，每维取「无」「极轻微」「轻微」「中轻度」「中度」「较强烈」「强烈」「极强烈」。1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained(
4 "zzoceanpie/Qwen3-1.7B-Yukari-SFT-v2",
5 torch_dtype="auto", device_map="auto", trust_remote_code=True
6)
7tokenizer = AutoTokenizer.from_pretrained("zzoceanpie/Qwen3-1.7B-Yukari-SFT-v2")
8
9tags = "[<|中度喜悦|><|轻微愤怒|><|轻微悲伤|><|无恐惧|><|无厌恶|><|无惊讶|><|轻微信任|><|中度期待|>]"
10prompt = f"{tags}\n你觉得人类最有趣的地方是什么？"
11
12messages = [{"role": "user", "content": prompt}]
13text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
14inputs = tokenizer(text, return_tensors="pt").to(model.device)
15outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.8)
16print(tokenizer.decode(outputs[0], skip_special_tokens=True))1from llama_cpp import Llama
2
3model = Llama(model_path="Qwen3-1.7B-Yukari-SFT-f16.gguf", n_ctx=2048, n_gpu_layers=-1)
4response = model.create_chat_completion(
5 messages=[{"role": "user", "content": prompt}],
6 max_tokens=200, temperature=0.8
7)
8print(response["choices"][0]["message"]["content"])This model is a fan-made derivative work based on Touhou Project. Touhou Project is (C) Team Shanghai Alice / ZUN. Please refer to the official guidelines for Touhou fan content.