RX5950XT

silicon-based-girlfriend

README

License: apache-2.0

Model Details / 模型資訊

Table with columns: 項目, 內容
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

Table with columns: 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

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。

bash

# llama.cpp./llama-cli -m silicon-gf-q8_0.gguf -c 8192 --temp 0.8

Option 2: LoRA Adapter with transformers + PEFT

python

from peft import PeftModelfrom 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

bash

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

Training Loss Eval Loss

Dataset / 訓練資料集

倉庫：RX5950XTP/silicon-girlfriend-dataset
格式：ShareGPT（system + conversations with from/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_nothink chat 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）

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

RX5950XT

Model Tree

Base

Qwen/Qwen3.5-4B

Adapter

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Model Details / 模型資訊

Table with columns: 項目, 內容
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

Table with columns: 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

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。

bash

# llama.cpp./llama-cli -m silicon-gf-q8_0.gguf -c 8192 --temp 0.8

Option 2: LoRA Adapter with transformers + PEFT

python

from peft import PeftModelfrom 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

bash

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

Training Loss Eval Loss

Dataset / 訓練資料集

倉庫：RX5950XTP/silicon-girlfriend-dataset
格式：ShareGPT（system + conversations with from/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_nothink chat 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）