初始化项目，由ModelHub XC社区提供模型

Model: SPAISS6F1/qwen-1b-pruned-th
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,125 @@
+---
+license: apache-2.0
+language: [th]
+library_name: transformers
+pipeline_tag: text-generation
+tags: [thai, pruning, depth-pruning, layer-dropping]
+---
+
+# qwen-1b-pruned-th
+
+โมเดลภาษาไทยขนาดเล็กที่ได้จากการ **Depth Pruning (Layer Dropping)** ของ `Qwen/Qwen2.5-3B`
+แล้วทำ **Healing SFT** เพื่อกู้ความสามารถกลับมา
+
+| | |
+|---|---|
+| Base model | `Qwen/Qwen2.5-3B` |
+| Base size | 3.09B (36 layers) |
+| **โมเดลนี้** | **1.70B** (เก็บ 18 layers) |
+| Layers ที่เก็บ | [0-8, 27-35] (ตัด layer กลาง เก็บหัว+ท้าย) |
+| Healing data | SEA-PILE v2 Thai (~8,000 docs) |
+| Hardware | NVIDIA A100-40GB (Lanta HPC) |
+| Requires | `transformers>=4.44`, accelerate |
+
+---
+
+## Pipeline การสร้างโมเดล (ทำซ้ำได้)
+
+### ขั้นที่ 1 — Depth Pruning (Layer Dropping)
+ตัด decoder layer ตรงกลางทิ้ง (มักทำงานซ้ำซ้อน) เก็บเฉพาะ layer หัว (เข้าใจ input)
+และ layer ท้าย (สร้าง output) — **embedding / lm_head / norm คงเดิม** จึงไม่พัง dimension
+
+```python
+import torch
+from transformers import AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B", torch_dtype=torch.bfloat16)
+
+# หา text-decoder layer list (เลี่ยง vision encoder กรณี multimodal)
+holder, layers = None, None
+for _, mod in model.named_modules():
+    L = getattr(mod, "layers", None)
+    if isinstance(L, torch.nn.ModuleList) and len(L) and hasattr(L[0], "self_attn"):
+        holder, layers = mod, L
+        if "language" in _.lower() or "text" in _.lower():
+            break
+N = len(layers)
+
+# เก็บ 18 จาก 36 layers: หัว + ท้าย
+keep = [0,1,2,3,4,5,6,7,8, 27,28,29,30,31,32,33,34,35]
+holder.layers = torch.nn.ModuleList([layers[i] for i in keep])
+
+# อัปเดต config (รองรับ nested text_config ของ Gemma3)
+for c in {model.config, getattr(model.config, "text_config", model.config)}:
+    if getattr(c, "num_hidden_layers", None) is not None:
+        c.num_hidden_layers = len(keep)
+    lt = getattr(c, "layer_types", None)
+    if isinstance(lt, list) and len(lt) == N:
+        c.layer_types = [lt[i] for i in keep]
+
+# reindex layer_idx ของแต่ละ block (สำคัญต่อ KV cache)
+for i, lyr in enumerate(holder.layers):
+    if hasattr(lyr, "self_attn") and hasattr(lyr.self_attn, "layer_idx"):
+        lyr.self_attn.layer_idx = i
+```
+ผลลัพธ์: 3.09B -> **1.70B** (ยังไม่ถึง 1B เป๊ะ เพราะ embedding+lm_head+vocab ไม่ลดตาม layer)
+
+> หลัง prune โมเดลจะพ่น gibberish ทันที (เส้นประสาทถูกตัดขาด) -> ต้อง Healing ต่อ
+
+### ขั้นที่ 2 — Healing SFT
+เทรนต่อด้วย causal-LM บน Thai corpus เพื่อให้ layer ที่เหลือกลับมาทำงานร่วมกัน
+
+```python
+from transformers import Trainer, TrainingArguments, DataCollatorForLanguageModeling
+from datasets import load_dataset
+
+ds = load_dataset("SPAISS6F1/spai-ss6-llm-1b-thai-corpus", split="train")  # หรือ SEA-PILE v2 'th'
+tds = ds.map(lambda e: tok(e["text"], truncation=True, max_length=1024),
+             batched=True, remove_columns=ds.column_names)
+
+model.gradient_checkpointing_enable(); model.config.use_cache = False
+args = TrainingArguments(output_dir="out", num_train_epochs=2,
+    per_device_train_batch_size=4, gradient_accumulation_steps=4,
+    learning_rate=1e-4, lr_scheduler_type="cosine", warmup_ratio=0.03, bf16=True)
+Trainer(model=model, args=args, train_dataset=tds,
+        data_collator=DataCollatorForLanguageModeling(tok, mlm=False)).train()
+```
+
+**Hyperparameters:**
+- Learning rate: `1e-4` (สูงกว่าปกติเพื่อสมานแผล) | Epochs: 2
+- Batch 4 x grad-accum 4 (effective 16) | max_len 1024 | bf16
+- Optimizer: AdamW + cosine schedule, warmup 3%
+- Env: conda myenv (transformers 4.49)
+
+### ขั้นที่ 3 — Save
+```python
+model.config.use_cache = True
+try:
+    model.save_pretrained("out", safe_serialization=True)
+except RuntimeError:        # Gemma3: tied embeddings -> fallback .bin
+    model.save_pretrained("out", safe_serialization=False)
+```
+โมเดลนี้ save เป็น: `model.safetensors`
+
+---
+
+## วิธีใช้ (Inference)
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+m = "SPAISS6F1/qwen-1b-pruned-th"
+tok = AutoTokenizer.from_pretrained(m)
+model = AutoModelForCausalLM.from_pretrained(m, torch_dtype=torch.bfloat16, device_map="cuda")
+ids = tok("ปัญญาประดิษฐ์ คือ", return_tensors="pt").to(model.device)
+out = model.generate(**ids, max_new_tokens=120, do_sample=True,
+                     temperature=0.7, top_p=0.9, repetition_penalty=1.3)
+print(tok.decode(out[0], skip_special_tokens=True))
+```
+
+## ข้อควรรู้ / ข้อจำกัด
+- เป็น **pruned base ที่ heal ด้วย raw web corpus** -> ไวยากรณ์ไทยลื่นไหลดี
+  แต่ **ข้อเท็จจริงและการคิดเลขยังอ่อน** (ยังไม่ผ่าน instruction tuning)
+- แนะนำ `repetition_penalty >= 1.2` กันการวนซ้ำ
+- เหมาะเป็น **base สำหรับ fine-tune ต่อด้วย instruction dataset** มากกว่าใช้ตอบตรง ๆ
+- การตัด layer 50% เป็นการตัดที่ค่อนข้างหนัก (งานวิจัย เช่น ShortGPT แนะ ~25%);
+  ถ้าต้องการคุณภาพสูงขึ้นควร heal นานขึ้น/ตัดเบาลง

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ed5fc8999d73e2ee7766d6c682a8fd92a1e0813daa506d6c653032e2262929
+size 3397130560

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}