Update README.md

README.md

@@ -45,6 +45,147 @@ gguf_f16: [tinyllama-coder-py-4bit-v10-unsloth.F16.gguf](https://huggingface.co/
 gguf_Q4_K_M: [tinyllama-coder-py-4bit-v10-unsloth.Q4_K_M.gguf](https://huggingface.co/Ramikan-BR/tinyllama-coder-py-4bit-v10/blob/main/tinyllama-coder-py-4bit-v10-unsloth.Q4_K_M.gguf)
 gguf_Q8_0: [tinyllama-coder-py-4bit-v10-unsloth.Q8_0.gguf](https://huggingface.co/Ramikan-BR/tinyllama-coder-py-4bit-v10/blob/main/tinyllama-coder-py-4bit-v10-unsloth.Q8_0.gguf)
 
+#### Training Hyperparameters
+
+Notebook [Unsloath](https://github.com/unslothai/unsloth) that I used for AI refinement: [TinyLlama](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) 
+```python
+
+%%capture
+# Installs Unsloth, Xformers (Flash Attention) and all other packages!
+!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install --no-deps xformers trl peft accelerate bitsandbytes # xformers "xformers<0.0.26"
+
+import os
+from google.colab import drive
+drive.mount('/content/drive')
+
+from unsloth import FastLanguageModel
+import torch
+max_seq_length = 4096 # 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/mistral-7b-bnb-4bit",
+    "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
+    "unsloth/llama-2-7b-bnb-4bit",
+    "unsloth/llama-2-13b-bnb-4bit",
+    "unsloth/codellama-34b-bnb-4bit",
+    "unsloth/tinyllama-bnb-4bit",
+    "unsloth/gemma-7b-bnb-4bit", # New Google 6 trillion tokens model 2.5x faster!
+    "unsloth/gemma-2b-bnb-4bit",
+] # More models at https://huggingface.co/unsloth
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "Ramikan-BR/tinyllama-coder-py-4bit_LORA-v9", # "unsloth/tinyllama" for 16bit loading
+    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 = 256, # 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 = 512,
+    lora_dropout = 0, # Currently only supports dropout = 0
+    bias = "none",    # Currently only supports bias = "none"
+    use_gradient_checkpointing = True, # @@@ IF YOU GET OUT OF MEMORY - set to True @@@
+    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. Write a response that appropriately completes the request.
+### Input:
+{}
+
+### Output:
+{}"""
+
+EOS_TOKEN = tokenizer.eos_token
+def formatting_prompts_func(examples):
+    inputs       = examples["problem"]
+    outputs      = examples["solution"]
+    texts = []
+    for input, output in zip(inputs, outputs):
+        # Must add EOS_TOKEN, otherwise your generation will go on forever!
+        text = alpaca_prompt.format(input, output) + EOS_TOKEN
+        texts.append(text)
+    return { "text" : texts}
+pass
+
+from datasets import load_dataset
+dataset = load_dataset('json', data_files='/content/drive/MyDrive/data-oss_instruct-py-10.jsonl', split='train')
+dataset = dataset.map(formatting_prompts_func, batched=True)
+
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from unsloth import is_bfloat16_supported
+from transformers.utils import logging
+logging.set_verbosity_info()
+
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = dataset,
+    dataset_text_field = "text",
+    max_seq_length = max_seq_length,
+    dataset_num_proc = 2,
+    packing = True, # Packs short sequences together to save time!
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        gradient_accumulation_steps = 256,
+        warmup_ratio = 0.1,
+        num_train_epochs = 2,
+        learning_rate = 2e-4,
+        fp16 = not torch.cuda.is_bf16_supported(),
+        bf16 = torch.cuda.is_bf16_supported(),
+        logging_steps = 1,
+        optim = "adafactor", # adamw_torch ou adamw_torch_fused +10% velocidade ou adafactor ou adamw_8bit
+        weight_decay = 0.1,
+        lr_scheduler_type = "linear",
+        seed = 3407,
+        output_dir = "outputs",
+    ),
+)
+
+trainer_stats = trainer.train()
+
+model.save_pretrained("lora_model") # Local saving
+tokenizer.save_pretrained("lora_model")
+model.push_to_hub("Ramikan-BR/tinyllama-coder-py-4bit_LORA-v10", token = "hf_...") # Online saving
+tokenizer.push_to_hub("Ramikan-BR/tinyllama-coder-py-4bit_LORA-v10", token = "hf_...") # Online saving
+
+# Merge to 16bit
+model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
+model.push_to_hub_merged("Ramikan-BR/tinyllama-coder-py-4bit-v10", tokenizer, save_method = "merged_16bit", token = "hf_...")
+
+# Merge to 4bit
+if False: model.save_pretrained_merged("model", tokenizer, save_method = "merged_4bit",)
+if False: model.push_to_hub_merged("Ramikan-BR/tinyllama-coder-py-4bit-v10", tokenizer, save_method = "merged_4bit", token = "hf_...")
+
+# Just LoRA adapters
+if False: model.save_pretrained_merged("model", tokenizer, save_method = "lora",)
+if False: model.push_to_hub_merged("Ramikan-BR/tinyllama-coder-py-4bit-v10", tokenizer, save_method = "lora", token = "hf_...")
+
+# Save to 8bit Q8_0
+model.save_pretrained_gguf("model", tokenizer,)
+model.push_to_hub_gguf("Ramikan-BR/tinyllama-coder-py-4bit-v10", tokenizer, token = "hf_...")
+
+# Save to 16bit GGUF
+model.save_pretrained_gguf("model", tokenizer, quantization_method = "f16")
+model.push_to_hub_gguf("Ramikan-BR/tinyllama-coder-py-4bit-v10", tokenizer, quantization_method = "f16", token = "hf_...")
+
+# Save to q4_k_m GGUF
+model.save_pretrained_gguf("model", tokenizer, quantization_method = "q4_k_m")
+model.push_to_hub_gguf("Ramikan-BR/tinyllama-coder-py-4bit-v10", tokenizer, quantization_method = "q4_k_m", token = "hf_...")
+
+Parameters: 
+
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.