Update README.md

README.md

@@ -1,52 +1,53 @@
----
-library_name: transformers
-license: apache-2.0
-datasets:
-- benchang1110/pretrainedtw
-- HuggingFaceTB/cosmopedia-100k
-language:
-- zh
-widget:
-  - text: '在很久以前，這座島上'
-    example_title: Example1
-
----
-
-# Model Card for Model ID
-
-This is a continue-pretrained version of [Tinyllama](TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) tailored for traditional Chinese. The continue-pretraining dataset contains roughly 2B tokens.
-
-# Usage
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-
-def generate_response(input):
-    '''
-    simple test for the model
-    '''
-    # tokenzize the input
-    tokenized_input = tokenizer.encode_plus(input, return_tensors='pt').to(device)
-    
-    # generate the response
-    outputs = model.generate(
-        input_ids=tokenized_input['input_ids'], 
-        attention_mask=tokenized_input['attention_mask'],
-        pad_token_id=tokenizer.pad_token_id,
-        do_sample=False,
-        repetition_penalty=1.3,
-        max_length=500
-    )
-    
-    # decode the response
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-if __name__ == '__main__':
-    device = 'cuda' if torch.cuda.is_available() else 'cpu'
-    model = AutoModelForCausalLM.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat",device_map=device,torch_dtype=torch.bfloat16)
-    tokenizer = AutoTokenizer.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat")
-    while(True):
-        text = input("input a simple prompt:")
-        print('System:', generate_response(text))
-```
-Using bfloat16, the VRAM required is around 3GB!!! 
+---
+library_name: transformers
+license: apache-2.0
+datasets:
+- DavidLanz/TaiwanChat
+- benchang1110/pretrainedtw
+- HuggingFaceTB/cosmopedia-100k
+language:
+- zh
+widget:
+  - text: '在很久以前，這座島上'
+    example_title: Example1
+
+---
+
+# Model Card for Model ID
+
+This is a continue-pretrained version of [Tinyllama](TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) tailored for traditional Chinese. The continue-pretraining dataset contains roughly 2B tokens.
+
+# Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+def generate_response(input):
+    '''
+    simple test for the model
+    '''
+    # tokenzize the input
+    tokenized_input = tokenizer.encode_plus(input, return_tensors='pt').to(device)
+    
+    # generate the response
+    outputs = model.generate(
+        input_ids=tokenized_input['input_ids'], 
+        attention_mask=tokenized_input['attention_mask'],
+        pad_token_id=tokenizer.pad_token_id,
+        do_sample=False,
+        repetition_penalty=1.3,
+        max_length=500
+    )
+    
+    # decode the response
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+if __name__ == '__main__':
+    device = 'cuda' if torch.cuda.is_available() else 'cpu'
+    model = AutoModelForCausalLM.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat",device_map=device,torch_dtype=torch.bfloat16)
+    tokenizer = AutoTokenizer.from_pretrained("DavidLanz/Taiwan-tinyllama-v1.0-chat")
+    while(True):
+        text = input("input a simple prompt:")
+        print('System:', generate_response(text))
+```
+Using bfloat16, the VRAM required is around 3GB!!!