python

README.md

@@ -13,6 +13,7 @@ base_model:
 ## Uses
 以下のコードで40分ほどでElyza-tasks-TV-100の推論が終了します。
 
+```python:inference.py  
 #推論時のコード
 
 !pip install -U bitsandbytes  
@@ -46,63 +47,64 @@ bnb_config = BitsAndBytesConfig(
 )  
 
 # Load model
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    quantization_config=bnb_config,
-    device_map="auto",
-    token = HF_TOKEN
-)
+model = AutoModelForCausalLM.from_pretrained(  
+    model_id,  
+    quantization_config=bnb_config,  
+    device_map="auto",  
+    token = HF_TOKEN  
+)  
 
 # Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
-# 元のモデルにLoRAのアダプタを統合。
-model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
-model.eval()
-
-datasets = []
-with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
-    item = ""
-    for line in f:
-      line = line.strip()
-      item += line
-      if item.endswith("}"):
-        datasets.append(json.loads(item))
-        item = ""
-
-
-results = []
-for data in tqdm(datasets):
-
-  input = data["input"]
-
-  prompt = f"""### 指示
-  {input}
-  ### 回答
-  """
-
-  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
-  attention_mask = torch.ones_like(tokenized_input)
-  with torch.no_grad():
-      outputs = model.generate(
-          tokenized_input,
-          attention_mask=attention_mask,
-          max_new_tokens=512,
-          do_sample=False,
-          repetition_penalty=1.2,
-          pad_token_id=tokenizer.eos_token_id
-      )[0]
-  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
-
-  results.append({"task_id": data["task_id"], "input": input, "output": output})
-
-import re
-jsonl_id = re.sub(".*/", "", adapter_id)
-with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
-    for result in results:
-        json.dump(result, f, ensure_ascii=False)  # ensure_ascii=False for handling non-ASCII characters
-        f.write('\n')
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)  
+# 元のモデルにLoRAのアダプタを統合。  
+model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)  
+model.eval()  
+
+datasets = []  
+with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:  
+    item = ""  
+    for line in f:  
+      line = line.strip()  
+      item += line  
+      if item.endswith("}"):  
+        datasets.append(json.loads(item))  
+        item = ""  
+
+
+results = []  
+for data in tqdm(datasets):  
+
+  input = data["input"]  
+
+  prompt = f"""### 指示  
+  {input}  
+  ### 回答  
+  """  
+
+  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)  
+  attention_mask = torch.ones_like(tokenized_input)  
+  with torch.no_grad():  
+      outputs = model.generate(  
+          tokenized_input,  
+          attention_mask=attention_mask,  
+          max_new_tokens=512,  
+          do_sample=False,  
+          repetition_penalty=1.2,  
+          pad_token_id=tokenizer.eos_token_id  
+      )[0]  
+  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)  
+
+  results.append({"task_id": data["task_id"], "input": input, "output": output})  
+
+import re  
+jsonl_id = re.sub(".*/", "", adapter_id)  
+with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:  
+    for result in results:  
+        json.dump(result, f, ensure_ascii=False)  # ensure_ascii=False for handling non-ASCII characters  
+        f.write('\n')  
         
-#以上でjsonlファイルを得る。
+#以上でjsonlファイルを得る。  
+```
 
 ### Training Data