commit d7b82d3544adbc6c29cfd21f7958908704cac144 Author: ModelHub XC Date: Mon Jun 22 17:09:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: maywell/TinyWand-DPO Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..514c71e --- /dev/null +++ b/.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.json filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f6a8463 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +license: apache-2.0 +--- + +# **TinyWand-DPO** +

+ +

+ +# **한국어 모델 설명** + +**1.63B, 하찮은 크기의 SLM은 어떨까요?** + +## **모델 소개** +**TinyWand-DPO**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** +OPEN + +## **모델 성능** +TBD + +## **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-DPO") +model = AutoModelForCausalLM.from_pretrained( + "maywell/TinyWand-DPO", + 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]) +``` \ No newline at end of file diff --git a/TinyWand.png b/TinyWand.png new file mode 100644 index 0000000..9c209f5 Binary files /dev/null and b/TinyWand.png differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..28a3176 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "maywell/TinyWand-DPO", + "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 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c533f93 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.36.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..a9d3c9c --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b93d4b145e24ed6aad2d318a396381fecbd4f794529cc1638098effd616d2d +size 3257195328 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..21779d6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e +size 1842767 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..580d6d3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,41 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}