Update README.md

README.md

@@ -20,6 +20,13 @@ programming_language:
 library_name: transformers
 pipeline_tag: text-generation
 inference: false
+datasets:
+- databricks/databricks-dolly-15k
+- llm-jp/databricks-dolly-15k-ja
+- llm-jp/oasst1-21k-en
+- llm-jp/oasst1-21k-ja
+- llm-jp/oasst2-33k-en
+- llm-jp/oasst2-33k-ja
 ---
 # llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
 
@@ -56,8 +63,11 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("llm-jp/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0")
 model = AutoModelForCausalLM.from_pretrained("llm-jp/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0", device_map="auto", torch_dtype=torch.float16)
-text = "自然言語処理とは何か"
-tokenized_input = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt").to(model.device)
+chat = [
+    {"role": "system", "content": "以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。"},
+    {"role": "user", "content": "自然言語処理とは何か"},
+]
+tokenized_input = tokenizer.apply_chat_template(chat, add_generation_prompt=True, tokenize=True, return_tensors="pt").to(model.device)
 with torch.no_grad():
     output = model.generate(
         tokenized_input,
@@ -89,7 +99,7 @@ print(tokenizer.decode(output))
 
 - **Instruction tuning:**
   - **Hardware:** 8 A100 40GB GPUs ([mdx cluster](https://mdx.jp/en/))
-  - **Software:** [TRL](https://github.com/huggingface/trl), [PEFT](https://github.com/huggingface/peft), and [DeepSpeed](https://github.com/microsoft/DeepSpeed)
+  - **Software:** [TRL](https://github.com/huggingface/trl) and [DeepSpeed](https://github.com/microsoft/DeepSpeed)
 
 ## Tokenizer