Update README.md

README.md

@@ -1,22 +1,26 @@
 ---
-library_name: peft
+license: cc-by-sa-4.0
+datasets:
+- c-s-ale/alpaca-gpt4-data-zh
+language:
+- en
+- zh
 ---
-## Training procedure
 
+This model is an LoRA adapter file from finetuned Llama-2-13b-chat-hf model. This is an experimental model.
 
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
+This model is presented by IceBear-AI.
 
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-### Framework versions
+To run it, you need to:
+- Agree with Meta's agreements to download the Llama-2-13b-chat-hf model from here: https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
+- Clone this repository
+- Clone the Alpaca-LoRA repository from here: https://github.com/tloen/alpaca-lora
+- Use this command to run it:
+  -python generate.py \
+    --load_8bit \
+    --base_model 'PATH_TO_YOUR_LOCAL_LLAMA_2_13B_CHAT_HF' \
+    --lora_weights 'PATH_TO_YOUR_LOCAL_FILE_OF_THIS_MODEL'
 
-- PEFT 0.5.0.dev0
+You must agree with Meta/Llama-2's agreements to use this model.
 
-- PEFT 0.5.0.dev0
+If you would like to contact us, please don't hesitate to email to icebearai@163.com.