Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gguf/rx5950xt-digital-twin-v2-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,140 @@
+---
+license: apache-2.0
+language:
+  - zh
+base_model: Qwen/Qwen3.5-4B
+tags:
+  - digital-twin
+  - lora
+  - qlora
+  - conversational
+  - chinese
+  - traditional-chinese
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# rx5950xt Digital Twin v2 — Qwen3.5-4B QLoRA
+
+基於 [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) 微調的數位分身模型。
+透過 Discord 對話記錄微調，模仿特定使用者的語氣、用詞習慣與對話風格。
+
+## 模型描述
+
+| 項目 | 內容 |
+|------|------|
+| 基底模型 | Qwen/Qwen3.5-4B |
+| 微調方法 | QLoRA (4-bit NF4 + LoRA rank 8) |
+| 訓練框架 | [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory) |
+| 訓練資料 | ~1067 筆 Discord 對話 + [alpaca_gpt4_zh](https://huggingface.co/datasets/llamafactory/alpaca_gpt4_zh) 通用中文指令資料 |
+| 語言 | 繁體中文（臺灣） |
+| 授權 | Apache 2.0 |
+
+## 訓練細節
+
+### 防過擬合策略
+
+由於訓練資料量有限（~1067 筆），採用以下策略防止過擬合：
+
+- **資料混合**: 將個人對話資料與通用中文指令資料（alpaca_gpt4_zh）以約 1:2 比例混合
+- **低學習率**: 5e-5（相比一般 LoRA 的 2e-4）
+- **單輪訓練**: 僅 1 epoch，避免反覆記憶訓練資料
+- **較小 LoRA rank**: r=8（相比常見的 16-64）
+- **NEFTune 噪聲**: alpha=5.0，增加訓練穩定性
+- **LoRA Dropout**: 0.1
+
+### 訓練參數
+
+```yaml
+model: Qwen/Qwen3.5-4B (4-bit BNB quantized)
+lora_rank: 8
+lora_alpha: 16
+lora_dropout: 0.1
+learning_rate: 5e-5
+num_train_epochs: 1
+lr_scheduler: cosine
+warmup_steps: 20
+batch_size: 16 (effective, via gradient accumulation)
+optimizer: paged_adamw_8bit
+neftune_noise_alpha: 5.0
+cutoff_len: 512
+bf16: true
+```
+
+### 訓練結果
+
+| 指標 | 數值 |
+|------|------|
+| Train Loss | 2.397 |
+| Eval Loss | 2.349 |
+| 訓練時間 | ~2 小時 10 分鐘 |
+| 總步數 | 164 steps |
+| GPU | NVIDIA RTX 3070 Ti |
+
+> eval_loss < train_loss，表示模型未過擬合。
+
+![Training Loss](training_loss.png)
+
+## 檔案結構
+
+```
+.
+├── README.md                    # 本檔案
+├── train_config.yaml            # LLaMA Factory 訓練配置
+├── export_config_v2.yaml        # 模型匯出配置
+├── training_loss.png            # 訓練損失曲線
+├── adapter/                     # LoRA adapter 權重
+│   ├── adapter_model.safetensors
+│   ├── adapter_config.json
+│   ├── tokenizer.json
+│   ├── tokenizer_config.json
+│   └── chat_template.jinja
+└── gguf/                        # 量化版本
+    └── rx5950xt-digital-twin-v2-q8_0.gguf (Q8_0, 4.2 GB)
+```
+
+## 使用方式
+
+### 方式一：LM Studio / Ollama（推薦）
+
+直接下載 `gguf/rx5950xt-digital-twin-v2-q8_0.gguf`，在 LM Studio 或 Ollama 中載入即可。
+
+> 注意：聊天模板已修改為 nothink 模式（停用 Qwen3.5 的思考功能），回覆會直接輸出。
+
+### 方式二：Transformers + PEFT（載入 LoRA adapter）
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen3.5-4B",
+    torch_dtype="auto",
+    device_map="auto",
+    trust_remote_code=True,
+)
+model = PeftModel.from_pretrained(base_model, "RX5950XTP/rx5950xt-digital-twin-Qwen3.5-4B/adapter")
+tokenizer = AutoTokenizer.from_pretrained("RX5950XTP/rx5950xt-digital-twin-Qwen3.5-4B/adapter")
+
+messages = [
+    {"role": "system", "content": "你是 rx5950xt 的數位分身。"},
+    {"role": "user", "content": "你好！"},
+]
+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=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## 限制與注意事項
+
+- 訓練資料僅約 1067 筆 Discord 對話，覆蓋的話題和情境有限
+- 混合了通用中文指令資料以保留泛用能力，但可能稍微稀釋個人風格
+- 不適用於需要專業知識、事實查證或安全敏感的場景
+- 本模型僅供研究與娛樂用途
+
+## 致謝
+
+- [Qwen Team](https://huggingface.co/Qwen/Qwen3.5-4B) — 基底模型
+- [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory) — 訓練框架
+- [llama.cpp](https://github.com/ggml-org/llama.cpp) — GGUF 轉換

adapter/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "in_proj_b",
+    "k_proj",
+    "in_proj_a",
+    "in_proj_z",
+    "up_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a87334af894a7a8780bce99c29a6175cb99bf232640b0af6e37167083b6d2a
+size 65003848

adapter/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

adapter/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

adapter/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

export_config_v2.yaml

@@ -0,0 +1,12 @@
+### model
+model_name_or_path: Qwen/Qwen3.5-4B
+adapter_name_or_path: saves/rx5950xt-digital-twin/qlora-v2
+template: qwen3_5_nothink
+finetuning_type: lora
+trust_remote_code: true
+
+### export
+export_dir: saves/rx5950xt-digital-twin/merged-v2
+export_size: 2
+export_device: cpu
+export_legacy_format: false

gguf/rx5950xt-digital-twin-v2-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d4b608ce84612c84d67deaef4971f9fe79828302c2d2b59ee3160a3a720aa1
+size 4482402496

train_config.yaml

@@ -0,0 +1,50 @@
+### model
+model_name_or_path: Qwen/Qwen3.5-4B
+quantization_bit: 4
+quantization_method: bnb
+trust_remote_code: true
+upcast_layernorm: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_rank: 8
+lora_alpha: 16
+lora_target: all
+lora_dropout: 0.1
+
+### dataset
+dataset: rx5950xt_discord,alpaca_gpt4_zh
+template: qwen3_5_nothink
+cutoff_len: 512
+max_samples: 2000
+preprocessing_num_workers: 1
+dataloader_num_workers: 0
+
+### output
+output_dir: saves/rx5950xt-digital-twin/qlora-v2
+logging_steps: 10
+save_steps: 200
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 16
+learning_rate: 5.0e-5
+num_train_epochs: 1.0
+lr_scheduler_type: cosine
+warmup_steps: 20
+bf16: true
+gradient_checkpointing: true
+optim: paged_adamw_8bit
+neftune_noise_alpha: 5.0
+
+### eval
+val_size: 0.05
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 200