Update README.md

README.md

@@ -13,10 +13,165 @@ language:
 
 # Uploaded  model
 
-- **Developed by:** H-INO
 - **License:** apache-2.0
 - **Finetuned from model :** llm-jp/llm-jp-3-13b
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# The models have been fine-tuned on the following datasets. 
+
+Dataset:ichikara-instruction-003-001-1.json
+description:A manually constructed instruction dataset
+
+データセット作成チーム： 関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎. 
+ichikara-instruction: LLMのための日本語インストラクションデータの構築. 言語処理学会第30回年次大会(2024)
+
+I’m grateful to everyone here.
+
+# Usage 
+
+```python
+!pip uninstall unsloth -y
+!pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install ipywidgets --upgrade
+
+import torch
+if torch.cuda.get_device_capability()[0] >= 8:
+    !pip install --no-deps packaging ninja einops "flash-attn>=2.6.3"
+
+HF_TOKEN = "HF_TOKEN" #@param {type:"string"}
+
+from unsloth import FastLanguageModel
+import torch
+max_seq_length = 512
+dtype = None
+load_in_4bit = True
+
+model_id = "llm-jp/llm-jp-3-13b"
+new_model_id = "model name" 
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name=model_id,
+    dtype=dtype,
+    load_in_4bit=load_in_4bit,
+    trust_remote_code=True,
+)
+
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 32,
+    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
+                      "gate_proj", "up_proj", "down_proj",],
+    lora_alpha = 32,
+    lora_dropout = 0.05,
+    bias = "none",
+    use_gradient_checkpointing = "unsloth",
+    random_state = 3407,
+    use_rslora = False,
+    loftq_config = None,
+    max_seq_length = max_seq_length,
+)
+
+from datasets import load_dataset
+dataset = load_dataset("json", data_files="./ichikara-instruction-003-001-1.json")
+
+prompt = """### 指示
+{}
+### 回答
+{}"""
+
+EOS_TOKEN = tokenizer.eos_token 
+def formatting_prompts_func(examples):
+    input = examples["text"] 
+    output = examples["output"] 
+    text = prompt.format(input, output) + EOS_TOKEN 
+    return { "formatted_text" : text, } 
+pass
+
+dataset = dataset.map(
+    formatting_prompts_func,
+    num_proc= 4, 
+)
+
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from unsloth import is_bfloat16_supported
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset=dataset["train"],
+    max_seq_length = max_seq_length,
+    dataset_text_field="formatted_text",
+    packing = False,
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        gradient_accumulation_steps = 4,
+        num_train_epochs = 1,
+        logging_steps = 10,
+        warmup_steps = 10,
+        save_steps=100,
+        save_total_limit=2,
+        max_steps=-1,
+        learning_rate = 2e-4,
+        fp16 = not is_bfloat16_supported(),
+        bf16 = is_bfloat16_supported(),
+        group_by_length=True,
+        seed = 3407,
+        output_dir = "outputs",
+        report_to = "none",
+    ),
+)
+
+trainer_stats = trainer.train()
+
+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 = ""
+
+from tqdm import tqdm
+
+FastLanguageModel.for_inference(model)
+
+results = []
+for dt in tqdm(datasets):
+  input = dt["input"]
+
+  prompt = f"""### 指示\n{input}\n### 回答\n"""
+
+  inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
+
+  outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)
+  prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
+
+  results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
+
+from tqdm import tqdm
+
+FastLanguageModel.for_inference(model)
+
+results = []
+for dt in tqdm(datasets):
+  input = dt["input"]
+
+  prompt = f"""### 指示\n{input}\n### 回答\n"""
+
+  inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
+
+  outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2)
+  prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
+
+  results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
+
+with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
+    for result in results:
+        json.dump(result, f, ensure_ascii=False)
+        f.write('\n')