Update README.md

README.md

@@ -115,6 +115,40 @@ demo = gr.ChatInterface(
 demo.queue().launch()
 ```
 
+### Textstreamer
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+model_name = "aixsatoshi/Honyaku-7b-v2"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Define the streamer
+streamer = TextStreamer(tokenizer)
+
+# Define the English prompt
+english_prompt = """
+Machine translation accuracy varies greatly across languages.
+Key challenges include context understanding, idiomatic expressions, and syntactic differences.
+Advanced models leverage AI to enhance translation quality, focusing on nuances and cultural relevance.
+Continuous updates and training on diverse datasets are essential for improving accuracy and expanding language support, making global communication more accessible and effective.
+"""
+
+# Prepare the prompt for English to Japanese translation
+prompt = f"<english>: {english_prompt} </english>\n\n<japanese>:"
+
+# Tokenize the input text and move to CUDA device
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+
+# Generate the output using the model and streamer
+output = model.generate(**inputs, max_new_tokens=4096, do_sample=True, top_k=20, top_p=0.95, streamer=streamer)
+```
+
 # Base Model  
 [tokyotech-llm/Swallow-MS-7b-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1)