Update README.md

README.md

@@ -1,3 +1,56 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- llm-jp/databricks-dolly-15k-ja
+language:
+- ja
+library_name: transformers
+---
+## モデル
+
+- ベースモデル：[llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0)
+- 学習データセット：[llm-jp/databricks-dolly-15k-ja](https://huggingface.co/datasets/llm-jp/databricks-dolly-15k-ja)
+- 学習方式：フルパラメータチューニング
+
+## サンプル
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
+tokenizer = AutoTokenizer.from_pretrained(
+    "ryota39/llm-jp-1b-sft-15k"
+    )
+pad_token_id = tokenizer.pad_token_id
+
+model = AutoModelForCausalLM.from_pretrained(
+    "ryota39/llm-jp-1b-sft-15k",
+    device_map="auto",
+    torch_dtype=torch.float16,
+    )
+
+text = "東京の観光名所を教えてください。\n"
+tokenized_input = tokenizer.encode(
+    text,
+    add_special_tokens=False,
+    return_tensors="pt"
+    ).to(model.device)
+
+attention_mask = torch.ones_like(tokenized_input)
+attention_mask[tokenized_input == pad_token_id] = 0
+
+with torch.no_grad():
+    output = model.generate(
+        tokenized_input,
+        attention_mask=attention_mask,
+        max_new_tokens=128,
+        do_sample=False,
+        # top_p=0.8,
+        # temperature=0.8,
+        repetition_penalty=1.0
+    )[0]
+
+print(tokenizer.decode(output))
+
+```