Update README.md

README.md

@@ -59,4 +59,54 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - Pytorch 2.1.2+cu121
 - Datasets 2.14.5
-- Tokenizers 0.14.1
+- Tokenizers 0.14.1
+
+## Usage
+
+```python
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="ayousanz/japanese-mistral-0.3b-base")
+
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+import torch
+
+MODEL_NAME = "ayousanz/japanese-mistral-0.3b-base"
+torch.set_float32_matmul_precision('high')
+
+DEVICE = "cuda"
+if torch.cuda.is_available():
+    print("cuda")
+    DEVICE = "cuda"
+else:
+    print("cpu")
+    DEVICE = "cpu"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME,use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    trust_remote_code=True,
+).to(DEVICE)
+
+prompt = "大規模言語モデルとは、"
+
+inputs = tokenizer(prompt, add_special_tokens=False,return_tensors="pt").to(model.device)
+with torch.no_grad():
+
+    outputs = model.generate(
+        inputs["input_ids"],
+        max_new_tokens=256,
+        do_sample=True,
+        early_stopping=False,
+        top_p=0.95,
+        top_k=50,
+        temperature=0.9,
+        # streamer=streamer,
+        no_repeat_ngram_size=2,
+        num_beams=3
+    )
+
+outputs_txt = tokenizer.decode(outputs[0])
+print(outputs_txt)
+
+```