Rename README.md to 微调llama3.md

README.md

@@ -1,3 +0,0 @@
----
-license: apache-2.0
----

微调llama3.md

@@ -0,0 +1,294 @@
+---
+license: apache-2.0
+---
+```python
+!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+```
+
+```python
+!pip install --upgrade pip
+```
+
+```python
+!pip install --no-deps "xformers<0.0.26" "trl<0.9.0" peft accelerate bitsandbytes
+```
+
+```python
+from unsloth import FastLanguageModel
+import torch
+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/mistral-7b-v0.3-bnb-4bit",      # New Mistral v3 2x faster!
+    "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+    "unsloth/llama-3-8b-bnb-4bit",           # Llama-3 15 trillion tokens model 2x faster!
+    "unsloth/llama-3-8b-Instruct-bnb-4bit",
+    "unsloth/llama-3-70b-bnb-4bit",
+    "unsloth/Phi-3-mini-4k-instruct",        # Phi-3 2x faster!
+    "unsloth/Phi-3-medium-4k-instruct",
+    "unsloth/mistral-7b-bnb-4bit",
+    "unsloth/gemma-7b-bnb-4bit",             # Gemma 2.2x faster!
+] # More models at https://huggingface.co/unsloth
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "unsloth/llama-3-8b-bnb-4bit",
+    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
+)
+```
+
+```python
+# ========================================================
+# Test before training
+# ========================================================
+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:
+{}"""
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+        "请把现代汉语翻译成古文", # instruction
+        "其品行廉正，所以至死也不放松对自己的要求。", # input
+        "", # output - leave this blank for generation!
+    )
+], return_tensors = "pt").to("cuda")
+
+from transformers import TextStreamer
+text_streamer = TextStreamer(tokenizer)
+_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)
+```
+
+```python
+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
+)
+```
+
+```python
+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("Asuncom/shiji-qishiliezhuan", split = "train")
+dataset = dataset.map(formatting_prompts_func, batched = True,)
+```
+
+```python
+from trl import SFTTrainer
+from transformers import TrainingArguments
+from unsloth import is_bfloat16_supported
+
+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 = 100,
+        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",
+    ),
+)
+```
+
+```python
+#@title Show current memory stats
+gpu_stats = torch.cuda.get_device_properties(0)
+start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)
+max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)
+print(f"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.")
+print(f"{start_gpu_memory} GB of memory reserved.")
+```
+
+```python
+import wandb
+
+# 初始化一个离线模式的W&B运行
+wandb.init(mode="offline", project="asuncom", entity="asuncom")
+```
+
+```python
+trainer_stats = trainer.train()
+```
+
+```python
+#@title Show final memory and time stats
+used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)
+used_memory_for_lora = round(used_memory - start_gpu_memory, 3)
+used_percentage = round(used_memory         /max_memory*100, 3)
+lora_percentage = round(used_memory_for_lora/max_memory*100, 3)
+print(f"{trainer_stats.metrics['train_runtime']} seconds used for training.")
+print(f"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.")
+print(f"Peak reserved memory = {used_memory} GB.")
+print(f"Peak reserved memory for training = {used_memory_for_lora} GB.")
+print(f"Peak reserved memory % of max memory = {used_percentage} %.")
+print(f"Peak reserved memory for training % of max memory = {lora_percentage} %.")
+```
+
+```python
+# alpaca_prompt = Copied from above
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+        "请把现代汉语翻译成古文", # instruction
+        "其品行廉正，所以至死也不放松对自己的要求。", # input
+        "", # output - leave this blank for generation!
+    )
+], return_tensors = "pt").to("cuda")
+
+from transformers import TextStreamer
+text_streamer = TextStreamer(tokenizer)
+_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)
+```
+
+```python
+model.save_pretrained("lora_model") # Local saving
+tokenizer.save_pretrained("lora_model")
+model.push_to_hub("Asuncom/Llama-3-8B-bnb-4bit-shiji", token = "hf_huggingface密钥XqWUItzvbAkNeKb") # Online saving
+tokenizer.push_to_hub("Asuncom/Llama-3-8B-bnb-4bit-shiji", token = "hf_gUYYWvhuggingface密钥zvbAkNeKb") # Online saving
+```
+
+```python
+if False:
+    from unsloth import FastLanguageModel
+    model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name = "lora_model", # YOUR MODEL YOU USED FOR TRAINING
+        max_seq_length = max_seq_length,
+        dtype = dtype,
+        load_in_4bit = load_in_4bit,
+    )
+    FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+
+# alpaca_prompt = You MUST copy from above!
+
+inputs = tokenizer(
+[
+    alpaca_prompt.format(
+        "What is a famous tall tower in Paris?", # instruction
+        "", # input
+        "", # output - leave this blank for generation!
+    )
+], return_tensors = "pt").to("cuda")
+
+from transformers import TextStreamer
+text_streamer = TextStreamer(tokenizer)
+_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)
+```
+
+```python
+# Merge to 16bit
+if False: model.save_pretrained_merged("model", tokenizer, save_method = "merged_16bit",)
+if False: model.push_to_hub_merged("Asuncom/Llama-3-8B-bnb-4bit-shiji", tokenizer, save_method = "merged_16bit", token = "hf_huggingface密钥XqWUItzvbAkNeKb")
+
+# Merge to 4bit
+if False: model.save_pretrained_merged("model", tokenizer, save_method = "merged_4bit",)
+if False: model.push_to_hub_merged("Asuncom/Llama-3-8B-bnb-4bit-shiji", tokenizer, save_method = "merged_4bit", token = "hf_gUYYWvhuggingface密钥zvbAkNeKb")
+
+# Just LoRA adapters
+if False: model.save_pretrained_merged("model", tokenizer, save_method = "lora",)
+if False: model.push_to_hub_merged("Asuncom/Llama-3-8B-bnb-4bit-shiji", tokenizer, save_method = "lora", token = "hf_gUYYWvvzxjWLhuggingface密钥eKb")
+```
+
+```python
+# Save to 8bit Q8_0
+if False: model.save_pretrained_gguf("model", tokenizer,)
+# Remember to go to https://huggingface.co/settings/tokens for a token!
+# And change hf to your username!
+if False: model.push_to_hub_gguf("Asuncom/Llama-3-8B-bnb-4bit-shiji", tokenizer, token = "")
+
+# Save to 16bit GGUF
+if False: model.save_pretrained_gguf("model", tokenizer, quantization_method = "f16")
+if False: model.push_to_hub_gguf("Asuncom/Llama-3-8B-bnb-4bit-shiji", tokenizer, quantization_method = "f16", token = "")
+
+# Save to q4_k_m GGUF
+if False: model.save_pretrained_gguf("model", tokenizer, quantization_method = "q4_k_m")
+if True: model.push_to_hub_gguf("Asuncom/Llama-3-8B-bnb-4bit-shiji", tokenizer, quantization_method = "q4_k_m", token = "hf_xxxxx")
+
+# Save to multiple GGUF options - much faster if you want multiple!
+if False:
+    model.push_to_hub_gguf(
+        "Asuncom/Llama-3-8B-bnb-4bit-shiji", # Change hf to your username!
+        tokenizer,
+        quantization_method = ["q4_k_m", "q8_0", "q5_k_m",],
+        token = "hf_huggingface密钥XqWUItzvbAkNeKb", # Get a token at https://huggingface.co/settings/tokens
+    )
+```
+
+```python
+model.push_to_hub_gguf(
+        "Asuncom/Llama-3-8B-bnb-4bit-shiji", # Change hf to your username!
+        tokenizer,
+        quantization_method = ["q4_k_m", "q8_0", "q5_k_m",],
+        token = "hf_huggingface密钥XqWUItzvbAkNeKb", # Get a token at https://huggingface.co/settings/tokens
+    )
+```
+
+```
+Saved GGUF to https://huggingface.co/Asuncom/Llama-3-8B-bnb-4bit-shiji
+Unsloth: Uploading GGUF to Huggingface Hub...
+Saved GGUF to https://huggingface.co/Asuncom/Llama-3-8B-bnb-4bit-shiji
+Unsloth: Uploading GGUF to Huggingface Hub...
+Saved GGUF to https://huggingface.co/Asuncom/Llama-3-8B-bnb-4bit-shiji
+Unsloth: Uploading GGUF to Huggingface Hub...
+Saved GGUF to https://huggingface.co/Asuncom/Llama-3-8B-bnb-4bit-shiji
+```