--- language: - en license: apache-2.0 library_name: transformers datasets: - Intel/orca_dpo_pairs - wikipedia - Open-Orca/OpenOrca inference: false model-index: - name: phi-2-upscaled-4B-instruct-v0.1 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 22.95 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=daekeun-ml/phi-2-upscaled-4B-instruct-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 28.68 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=daekeun-ml/phi-2-upscaled-4B-instruct-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 26.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=daekeun-ml/phi-2-upscaled-4B-instruct-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 40.92 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=daekeun-ml/phi-2-upscaled-4B-instruct-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 50.59 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=daekeun-ml/phi-2-upscaled-4B-instruct-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 0.76 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=daekeun-ml/phi-2-upscaled-4B-instruct-v0.1 name: Open LLM Leaderboard --- # phi-2-upscaled-4B-instruct-v0.1 ## Model Details This model is a model that performed continued pre-training and fine-tuning (instruction tuning) using the depth up-scaling (DUS) technique disclosed by Upstage. ### DUS(Depth Up-Scaling) and continued pre-training Similar to the methodology disclosed in the paper, we expanded from 32 transformer blocks to 48 blocks and then continued pre-training with the public dataset. Pre-training was performed for 3 days using 4 `ml.g5.48xlarge` instances from AWS (NVIDIA A10G GPU x 32ea). For pre-training, we used a sample set from Wikipedia. Note that performance is not guaranteed since only a small number of datasets were used for the experiment. The number of samples for training set is just around 1.5 million after tokenization. For distributed training, all weights were trained without adapter techniques, and sharding parallelization was performed with ZeRO-2. The presets are as follows. ```json { "fp16": { "enabled": "auto", "loss_scale": 0, "loss_scale_window": 1000, "initial_scale_power": 16, "hysteresis": 2, "min_loss_scale": 1 }, "bf16": { "enabled": "auto" }, "optimizer": { "type": "AdamW", "params": { "lr": "auto", "betas": "auto", "eps": "auto", "weight_decay": "auto" } }, "scheduler": { "type": "WarmupLR", "params": { "warmup_min_lr": "auto", "warmup_max_lr": "auto", "warmup_num_steps": "auto" } }, "zero_optimization": { "stage": 2, "allgather_partitions": true, "allgather_bucket_size": 2e8, "overlap_comm": true, "reduce_scatter": true, "reduce_bucket_size": 2e8, "contiguous_gradients": true, "cpu_offload": true }, "gradient_accumulation_steps": "auto", "gradient_clipping": "auto", "train_batch_size": "auto", "train_micro_batch_size_per_gpu": "auto" } ``` Some hyperparameters are listed below. ``` batch_size: 2 num_epochs: 1 learning_rate: 3e-4 gradient_accumulation_steps: 8 lr_scheduler_type: "linear" group_by_length: False ``` ### Fine-tuning After performing pre-training, instruction tuning and alignment tuning were performed sequentially. This process only took about 10 hours using AWS `ml.g5.24xlarge` (NVIDIA A10G GPU x 4ea). The dataset used for instruction tuning is a sample set of the OpenOrca dataset, and the dataset used for alignment tuning is Intel's orca_dpo_pairs dataset. All fine-tuning was learned using QLoRA, and the batch sizes were set to 3 and 1, respectively. We used 1,024 for the context length. 2,048 is also possible, but applying DPO often runs out of memory on 24GB GPU memory, so we settled on 1,024. Please see below for relevant code snippets. ```python peft_config = LoraConfig( r=8, lora_alpha=16, target_modules=["q_proj", "k_proj", "v_proj", "fc1", "fc2"], lora_dropout=0.05, bias="none", task_type="CAUSAL_LM", ) training_arguments = TrainingArguments( output_dir="logs", num_train_epochs=1, per_device_train_batch_size=batch_size, gradient_accumulation_steps=4, optim="paged_adamw_8bit", learning_rate=3e-4, weight_decay=0.001, bf16=True, max_grad_norm=0.3, max_steps=-1, warmup_ratio=0.03, group_by_length=True, lr_scheduler_type="cosine", report_to="wandb", ... ) ``` ### References - Base model: [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) - Paper: [SOLAR 10.7B](https://arxiv.org/abs/2312.15166) ## How to Get Started with the Model Since this model used ChatGPT's ChatML template, and tokens were added. You can use Hugging Face's chat template to create the prompt, but you can also create the prompt yourself with the code snippet below. ```python def create_inference_prompt(text): string = f"""<|im_start|>system You are a helpful AI assistant.<|im_end|> <|im_start|>user {text}<|im_end|> <|im_start|>assistant """ return string ``` If you want to simply see the inference results, please use the code snippet below. ```python from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer import torch torch.set_default_device("cuda") model_path = "daekeun-ml/phi-2-upscaled-4B-instruct-v0.1" model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype="auto", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained( model_path, use_fast=True, trust_remote_code=True ) # Format prompt message = [ {"role": "system", "content": "You are a helpful AI assistant. Generate appropriate answers to given questions."}, {"role": "user", "content": "What is a Large Language Model?"} ] prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False) inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False) outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, top_p=0.9, temperature=0.5, repetition_penalty=1.2) text = tokenizer.batch_decode(outputs)[0] print(text) ``` ## Notes ### License Apache 2.0; The license of phi-2 is MIT, but the license of the orca dataset used for training is apache 2.0. ### Caution This model was created as a personal experiment, unrelated to the organization I work for. The model may not operate correctly because separate verification was not performed. Please be careful unless it is for personal experimentation or PoC (Proof of Concept)! # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_daekeun-ml__phi-2-upscaled-4B-instruct-v0.1) | Metric |Value| |---------------------------------|----:| |Avg. |28.45| |AI2 Reasoning Challenge (25-Shot)|22.95| |HellaSwag (10-Shot) |28.68| |MMLU (5-Shot) |26.80| |TruthfulQA (0-shot) |40.92| |Winogrande (5-shot) |50.59| |GSM8k (5-shot) | 0.76|