Update README.md

README.md

@@ -12,16 +12,97 @@ language:
 - ja
 ---
 
+# Usage:
+
 To use in code:
 
 ```python
-from transformers import LlamaForCausalLM, LlamaTokenizer
+import torch
+import peft
+from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
+
+tokenizer = LlamaTokenizer.from_pretrained(
+    "decapoda-research/llama-7b-hf"
+    )
 
 model = LlamaForCausalLM.from_pretrained(
-            "tamdiep106/alpaca_lora_ja_en_emb-7b",
-             load_in_8bit=False,
-             torch_dtype=torch.float16,
-             device_map="auto"
+    "tamdiep106/alpaca_lora_ja_en_emb-7b",
+    load_in_8bit=False,
+    device_map="auto",
+    torch_dtype=torch.float16
+    )
+
+tokenizer.pad_token_id = 0  # unk. we want this to be different from the eos token
+tokenizer.bos_token_id = 1
+tokenizer.eos_token_id = 2
+```
+To try out this model, use this colab space
+https://colab.research.google.com/drive/1kVcN0L_n5lwhFlIqDkNbLNURboifgbBO?usp=sharing
+
+Japanese prompt:
+
+```python
+Instruction_input_JP = 'あなたはアシスタントです。以下に、タスクを説明する指示と、さらなるコンテキストを提供する入力を組み合わせます。 リクエストを適切に完了するレスポンスを作成します。'
+instruction_no_input_JP = 'あなたはアシスタントです。以下はタスクを説明する指示です。 リクエストを適切に完了するレスポンスを作成します。'
+
+prompt = """{}
+### Instruction:
+{}
+
+### Response:"""
+
+if input=='':
+    prompt = prompt.format(
+        instruction_no_input_JP, instruction
+        )
+else:
+    prompt = prompt.format("{}\n\n### input:\n{}""").format(
+        Instruction_input_JP, instruction, input
         )
-tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")
-```
+```
+
+English prompt:
+
+```python
+instruction_input_EN = 'You are an Assistant, below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.'
+instruction_no_input_EN = 'You are an Assistant, below is an instruction that describes a task. Write a response that appropriately completes the request.'
+
+prompt = """{}
+### Instruction:
+{}
+
+### Response:"""
+
+instruction = "4 + 4 = ?" #@param {type:"string"}
+input = "" #@param {type:"string"}
+
+if input=='':
+    prompt = prompt.format(
+        instruction_no_input_EN, instruction
+        )
+else:
+    prompt = prompt.format("{}\n\n### input:\n{}""").format(
+        instruction_input_EN, instruction, input
+        )
+```
+
+Use this code to decode output of model
+
+```python
+for s in generation_output.sequences:
+    result = tokenizer.decode(s).strip()
+    result = result.replace(prompt, '')
+    result = result.replace("<s>", "")
+    result = result.replace("</s>", "")
+    if result=='':
+        print('No output')
+        print(prompt)
+        print(result)
+        continue
+    print('\nResponse: ')
+
+    print(result)
+
+```
+
+# Training: