Silicon-Based-Girlfriend — QLoRA Adapter
基於 Qwen3.5-4B 的 QLoRA 微調 Adapter,訓練目標為沉浸式繁體中文角色扮演。本倉庫包含 LoRA Adapter 權重與 GGUF 格式模型。
Model Details / 模型資訊
| 項目 | 內容 |
|---|---|
| Base Model | Qwen/Qwen3.5-4B |
| Fine-tuning Method | QLoRA (4-bit NF4) |
| LoRA Rank | 32 |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| LoRA Target | All linear layers |
| Training Epochs | 5 |
| Context Length | 8192 tokens |
| Learning Rate | 1e-4 |
| LR Scheduler | Cosine |
| Optimizer | paged_adamw_8bit |
| Training Samples | 985 |
| Train Loss | 1.108 |
| Eval Loss | 1.434 |
| Hardware | NVIDIA RTX A6000 (48GB VRAM) |
| Training Time | ~19 hours |
| Framework | LLaMA-Factory |
| Chat Template | qwen3_5_nothink (non-thinking mode) |
Files / 檔案說明
| 檔案 | 說明 |
|---|---|
adapter_config.json |
LoRA 設定檔 |
adapter_model.safetensors |
LoRA 權重(248 MB) |
tokenizer_config.json |
Tokenizer 設定(含 nothink chat template) |
tokenizer.json |
Tokenizer |
vocab.json / merges.txt |
Vocabulary |
silicon-gf-q8_0.gguf |
Q8_0 量化 GGUF(4.2 GB,適用 llama.cpp / LM Studio) |
training_loss.png |
訓練 Loss 曲線 |
training_eval_loss.png |
評估 Loss 曲線 |
Usage / 使用方式
Option 1: GGUF (Recommended / 推薦)
直接在 LM Studio 或 llama.cpp 載入 silicon-gf-q8_0.gguf,無需額外安裝。
# llama.cpp
./llama-cli -m silicon-gf-q8_0.gguf -c 8192 --temp 0.8
Option 2: LoRA Adapter with transformers + PEFT
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_model = "Qwen/Qwen3.5-4B"
adapter = "RX5950XTP/silicon-based-girlfriend"
tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
messages = [
{"role": "user", "content": "嘿,你在幹嘛?"}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.8, do_sample=True)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
Option 3: LLaMA-Factory inference
llamafactory-cli chat \
--model_name_or_path Qwen/Qwen3.5-4B \
--adapter_name_or_path RX5950XTP/silicon-based-girlfriend \
--template qwen3_5_nothink \
--finetuning_type lora
Training Curves / 訓練曲線
Dataset / 訓練資料集
- 倉庫:RX5950XTP/silicon-girlfriend-dataset
- 格式:ShareGPT(
system+conversationswithfrom/value) - 筆數:985 筆多輪對話
- 語言:繁體中文(臺灣用語)
- 生成方式:由 Kimi K2.5 根據角色設定生成
Notes / 注意事項
- 本模型使用
qwen3_5_nothinkchat template,預設不啟用思考模式,回覆會直接輸出角色對話。 - 角色設定包含不良用語與成人主題,請自行評估使用場景。
- 模型以 QLoRA 訓練,推理時需搭配 base model(Qwen3.5-4B)一同載入,或直接使用 GGUF。
License
Apache 2.0(遵循 Qwen3.5-4B 原授權)
- Downloads last month
- 60
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support