初始化项目，由ModelHub XC社区提供模型

Model: maywell/TinyWand-SFT
Source: Original Platform

.gitattributes

@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+ 
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+---
+
+# **TinyWand-SFT**
+<p align="left">
+    <img src="./TinyWand.png" width="150"/>
+<p>
+
+# **한국어 모델 설명**
+
+**1.63B, 하찮은 크기의 SLM은 어떨까요?**
+
+## **모델 소개**
+**TinyWand-SFT**는 1.63B의 SLM 모델입니다. 이 모델은 1.63B라는 작은 크기를 가짐으로써 소형기기에서 구동되거나 큰 toks/s를 가질 수 있음과 동시에 강력한 성능을 보여줍니다.
+
+## **모델 라이센스**
+apache-2.0
+
+## **모델 성능**
+TBD
+
+### 한계
+작은 크기로 인하여 Insturct 파인튜닝 후 해당 템플릿이 아닐경우 제대로 응답하지 않는 모습을 보임. 특정 task에 사용한다면 프롬프팅보다는 파인튜닝을 권장함.
+
+같은 이유로 일반적인 벤치마크에서도 상당히 낮은 점수를 보임.
+
+## **학습 과정**
+TBD
+
+## **사용 안내**
+
+**추론에 필요한 VRAM**
+| 양자화 | 입력 토큰 수 | 출력 토큰 수 | 메모리 사용량 |
+|---|---|---|---|
+| bf16(base) | 64 | 256 | 3,888 MiB |
+| q4_K_M | 64 | 256 | 1,788 MiB |
+
+**프롬프트 템플릿**
+
+본 모델은 Alpaca 프롬프트 템플릿을 사용합니다. 
+
+해당 템플릿은 `apply_chat_template()`를 통해 [허깅페이스 템플릿](https://huggingface.co/docs/transformers/main/chat_templating)에서 확인 하실 수 있습니다.
+
+**아래 파이썬 코드를 사용하여 모델을 로드 및 사용 할 수 있습니다.**
+*transformers, torch가 사전 설치되어야함*
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda" # nvidia 그래픽카드 기준
+
+tokenizer = AutoTokenizer.from_pretrained("maywell/TinyWand-SFT")
+model = AutoModelForCausalLM.from_pretrained(
+    "maywell/TinyWand-SFT",
+    device_map="auto",
+    torch_dtype=torch.bfloat16, # 사용하는 장비가 bfloat16을 지원하지 않는 경우 torch.float16으로 바꿔주세요.
+)
+
+messages = [
+    {"role": "system", "content": "Below is an instruction that describes a task. Write a response that appropriately completes the request."}, # 비울 경우에도 동일하게 적용 됨.
+    {"role": "user", "content": "언어모델의 파라미터 수가 작으면 어떤 이점이 있어?"},
+]
+
+encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+
+model_inputs = encodeds.to(device)
+model.to(device)
+
+generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
+decoded = tokenizer.batch_decode(generated_ids)
+print(decoded[0])
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "maywell/TinyWand-SFT",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 34,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed8983a195453858f08a39f47e8975111391c32084c5844eda086d7f05e688d
+size 3257195328

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}