初始化项目，由ModelHub XC社区提供模型

Model: puwaer/Doujinshi-1.8b Source: Original Platform
2026-04-23 15:26:10 +08:00
commit 5e7d6ab7a9
8 changed files with 398800 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+language:
+- ja
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- not-for-all-audiences
+---
+
+# Doujinshi-1.8b
+Doujinshi-1.8bは、r18に特化した大規模言語モデル（LLM）であり、[llm-jp/llm-jp-3-1.8b](https://huggingface.co/llm-jp/llm-jp-3-1.8b) をベースに継続事前学習を行いました。本モデルは、同人コンテンツに関連する知識を強化するため、dmm.co.jp,dlsite.comよりスクレイピングし作成したr18向けデータセットを使用してトレーニングされています。
+
+モデルの出力に関して責任を負いません。各自自己責任で利用してください。
+
+| Model Variants | 
+| :--- |
+| [Doujinshi-1.8b](https://huggingface.co/puwaer/Doujinshi-1.8b) |
+| [Doujinshi-1.8b-instruct](https://huggingface.co/puwaer/Doujinshi-1.8b-instruct) |
+
+## モデル概要
+本モデルは、以下のデータセットを使用して追加学習を行いました。
+- [puwaer/dlsite-jp-v1](https://huggingface.co/datasets/puwaer/dlsite-jp-v1)
+- [puwaer/dmm-fanza-jp-v1](https://huggingface.co/datasets/puwaer/dmm-fanza-jp-v1)
+
+## 特徴
+- **ベースモデル**: [llm-jp/llm-jp-3-1.8b](https://huggingface.co/llm-jp/llm-jp-3-1.8b)
+- **日本語のテキスト生成に特化**
+- **r18に関する知識を強化**
+
+## 使用方法
+
+### モデルのロードと推論
+以下のコードでモデルをロードし、テキスト生成を行うことができます。
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("puwaer/Doujinshi-1.8b")
+model = AutoModelForCausalLM.from_pretrained("puwaer/Doujinshi-1.8b", device_map="auto", torch_dtype=torch.bfloat16)
+
+text = "avの良さを教えて"
+tokenized_input = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    output = model.generate(
+        tokenized_input,
+        max_new_tokens=100,
+        do_sample=True,
+        top_p=0.95,
+        temperature=0.7,
+        repetition_penalty=1.05,
+    )[0]
+
+print(tokenizer.decode(output))
+```
+
+## ライセンス
+本モデルは [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0) のもとで提供されます。
+
+## クレジット
+- **ベースモデル**: [llm-jp/llm-jp-3-1.8b](https://huggingface.co/llm-jp/llm-jp-3-1.8b)
+- **データセット提供**:
+  - [puwaer/dlsite-jp-v1](https://huggingface.co/datasets/puwaer/dlsite-jp-v1)
+  - [puwaer/dmm-fanza-jp-v1](https://huggingface.co/datasets/puwaer/dmm-fanza-jp-v1)
+- **作成方法詳細**: [特化型llm(Doujinshi-1.8b)の開発報告書①:開発の全体像](https://zenn.dev/articles/doujinshi_development_report_1)
+- **使用コード**: [github/puwaer](https://github.com/puwaer)
+
+## 開発支援のお願い
+現在、開発を続けていますが、クラウドGPUの価格が高く、十分な計算リソースを確保できずにいます。そのため、思い通りに開発が出来ていません。
+また、オープンソースの理念を大切にしており、プログラム・データセット・モデルを有料で公開するつもりはありません。そのため、金銭的に余裕のある方に支援していただけると大変助かります。
+TwitterのDMやご支援いただける方は、以下のプラットフォームよりお願いいたします。
+- [Twitter](https://x.com/puwaer)
+- [Zenn](https://zenn.dev/puwa/books/doujinshi_development_book)
+- [github sponsors](https://github.com/sponsors/puwaer)
+
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "None",
+  "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": 7168,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0",
+  "use_cache": false,
+  "vocab_size": 99584
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250f65b8610ad7671b19503616116bc5e9f8b68fb22567c694f2376030083d6c
+size 3735253552
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP|LLM-jp>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,98 @@
+{
+  "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
+    },
+    "3": {
+      "content": "<MASK|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<PAD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD|LLM-jp>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "99574": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS|LLM-jp>",
+  "eod_token": "</s>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<MASK|LLM-jp>",
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "<SEP|LLM-jp>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}