Update README.md

README.md

@@ -3,6 +3,86 @@ library_name: transformers
 tags: []
 ---
 
+# Evaluation with `elyza-tasks-100-TV_0.jsonl`
+
+```python
+# Put elyza-tasks-100-TV_0.jsonl in the current directory.
+
+# Needed for Google Colabolatory
+# !pip install -U bitsandbytes
+
+# Load the model
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+)
+import torch
+
+model_id = "kentof/llm-jp-3-13b-finetune"
+
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    quantization_config=bnb_config,
+    device_map="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+
+# Load tasks
+import json
+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 = ""
+
+# Generate
+from tqdm import tqdm
+
+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=100,
+          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})
+
+# Write a file
+with open(f"./{model_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')
+```
+
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->