Update README.md

README.md

@@ -1,6 +1,23 @@
 ---
 library_name: peft
+license: llama2
+tags:
+- medical
 ---
+⚠️⚠️⚠️ Only for research purpose. Do not use it for medical purpose. ⚠️⚠️⚠️
+
+# MedSwallow-70B🏥
+
+[東工大Swallow](tokyotech-llm/Swallow-70b-instruct-hf)をベースモデルとし, 医療Q&AデータセットでInstruction Tuningを施した医療ドメインの日本語LLMです.
+
+チューニングには独自で用意した米国医師国家試験(USMLE)を和訳したQ&Aデータセットを用いました.
+
+
+MedSwallow is a Japanese medical LLM for medical question-answering.
+
+MedSwallow is based on [Swallow-70B]((tokyotech-llm/Swallow-70b-instruct-hf)) and has passed instruction tuning with USMLE dataset translated in Japanese by our own.
+
+
 ## Training procedure
 
 
@@ -15,7 +32,19 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_quant_type: nf4
 - bnb_4bit_use_double_quant: True
 - bnb_4bit_compute_dtype: bfloat16
+
 ### Framework versions
+- PEFT 0.4.0
+
+
+## License
+
+ライセンスはLlama 2やSwallowと同じく, LLAMA 2 Community Licenseです.
+
+
+## How to cite
+```
+coming soon...
+```
 
 
-- PEFT 0.4.0