add files

test.py

@@ -0,0 +1,123 @@
+from unsloth import FastLanguageModel
+import torch
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from unsloth import is_bfloat16_supported
+
+max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+
+# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
+fourbit_models = [
+    "unsloth/Meta-Llama-3.1-8B-bnb-4bit",      # Llama-3.1 15 trillion tokens model 2x faster!
+    "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
+    "unsloth/Meta-Llama-3.1-70B-bnb-4bit",
+    "unsloth/Meta-Llama-3.1-405B-bnb-4bit",    # We also uploaded 4bit for 405b!
+    "unsloth/Mistral-Nemo-Base-2407-bnb-4bit", # New Mistral 12b 2x faster!
+    "unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit",
+    "unsloth/mistral-7b-v0.3-bnb-4bit",        # Mistral v3 2x faster!
+    "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+    "unsloth/Phi-3.5-mini-instruct",           # Phi-3.5 2x faster!
+    "unsloth/Phi-3-medium-4k-instruct",
+    "unsloth/gemma-2-9b-bnb-4bit",
+    "unsloth/gemma-2-27b-bnb-4bit",            # Gemma 2x faster!
+] # More models at https://huggingface.co/unsloth
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "unsloth/Meta-Llama-3.1-8B",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
+)
+model = FastLanguageModel.get_peft_model(
+    model,
+    r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
+    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
+                      "gate_proj", "up_proj", "down_proj",],
+    lora_alpha = 16,
+    lora_dropout = 0, # Supports any, but = 0 is optimized
+    bias = "none",    # Supports any, but = "none" is optimized
+    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
+    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
+    random_state = 3407,
+    use_rslora = False,  # We support rank stabilized LoRA
+    loftq_config = None, # And LoftQ
+)
+
+alpaca_prompt = """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:
+{}
+
+### Input:
+{}
+
+### Response:
+{}"""
+
+EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
+def formatting_prompts_func(examples):
+    instructions = examples["instruction"]
+    inputs       = examples["input"]
+    outputs      = examples["output"]
+    texts = []
+    for instruction, input, output in zip(instructions, inputs, outputs):
+        # Must add EOS_TOKEN, otherwise your generation will go on forever!
+        text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
+        texts.append(text)
+    return { "text" : texts, }
+pass
+
+from datasets import load_dataset
+dataset = load_dataset(path = "/home/alexander/GitHub/finetune", data_files="trainingsdata.jsonl", split="train")
+dataset = dataset.map(formatting_prompts_func, batched = True)
+
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = dataset,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    dataset_num_proc = 2,
+    packing = False, # Can make training 5x faster for short sequences.
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        gradient_accumulation_steps = 4,
+        warmup_steps = 5,
+        # num_train_epochs = 1, # Set this for 1 full training run.
+        max_steps = 120,
+        learning_rate = 2e-4,
+        fp16 = not is_bfloat16_supported(),
+        bf16 = is_bfloat16_supported(),
+        logging_steps = 1,
+        optim = "adamw_8bit",
+        weight_decay = 0.01,
+        lr_scheduler_type = "linear",
+        seed = 3407,
+        output_dir = "outputs",
+        report_to = "none", # Use this for WandB etc
+    ),
+)
+t_data = trainer.train()
+
+model.save_pretrained("lora_model_2")  # Local saving
+tokenizer.save_pretrained("lora_model_2")
+
+# Merge to 16bit
+if True: model.save_pretrained_merged("model_16_2", tokenizer, save_method = "merged_16bit",)
+if False: model.push_to_hub_merged("hf/model", tokenizer, save_method = "merged_16bit", token = "")
+
+# Merge to 4bit
+#if True: model.save_pretrained_merged("model", tokenizer, save_method = "merged_4bit",)
+if False: model.push_to_hub_merged("hf/model", tokenizer, save_method = "merged_4bit", token = "")
+
+# Just LoRA adapters
+if True:
+    model.save_pretrained("model_2")
+    tokenizer.save_pretrained("model_2")
+
+
+if True: model.save_pretrained_gguf("finetunedmodel_2", tokenizer,)