Update README.md

README.md

@@ -1,6 +1,92 @@
 ---
 library_name: peft
+license: llama2
+datasets:
+- izumi-lab/llm-japanese-dataset
+language:
+- ja
+pipeline_tag: text-generation
 ---
+
+# AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese
+
+This model is Llama-2-Chat 70B fine-tuned with a part of the following Japanese version of the alpaca dataset.
+
+https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset
+
+- 10000 steps
+- batch_size = 4
+
+
+## Copyright Notice
+
+This model is built on the copyright of Meta's LLaMA.
+
+Users of this model must also agree to Meta's license below.
+
+https://ai.meta.com/llama/
+
+
+## How to use
+
+```python
+import os
+os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2,3"
+import torch
+torch.cuda.empty_cache()
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoConfig
+
+# Load models
+model_id = "meta-llama/Llama-2-70b-chat-hf"
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
+config = AutoConfig.from_pretrained(model_id)
+config.pretraining_tp = 1 #LLama-2-70bなら必要
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, 
+                                             device_map="auto")
+
+# Load weights
+peft_name = "AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese"
+model_peft = PeftModel.from_pretrained(
+    model, 
+    peft_name, 
+    device_map="auto"
+)
+model_peft.eval()
+
+device = "cuda:0"
+
+inputs = tokenizer(text, return_tensors="pt").to(device)
+
+with torch.no_grad():
+  outputs = model.generate(**inputs,
+            temperature=0.0,
+            repetition_penalty=1.00)
+  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+  outputs = model_peft.generate(**inputs,
+            temperature=0.0,
+            repetition_penalty=1.00)
+  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Sample Responses
+
+```
+
+```
+
+
+
+
+
+
+
 ## Training procedure
 
 
@@ -17,4 +103,4 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.4.0
+- PEFT 0.4.0