Update README.md

README.md

@@ -1,3 +1,143 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+base_model:
+- unsloth/llama-3-8b-bnb-4bit
+pipeline_tag: text-generation
+tags:
+- conversational
+- llama
+- ollama
+- unsloth
+- gguf
+- 8b
+---
+
+# Training Process
+## Model + LoRA Loading
+```python
+from unsloth import FastLanguageModel
+import torch
+max_seq_length = 2048
+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.
+
+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
+)
+
+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
+    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
+)
+```
+
+## Dataset Preparation
+```python
+from datasets import load_dataset
+dataset = load_dataset(
+    "csv",
+    data_files = "/content/synth_data.csv",
+    split = "train",
+)
+
+from unsloth import to_sharegpt
+dataset = to_sharegpt(
+    dataset,
+    merged_prompt = "Labels: {available_entities}\n\nText: {text}\n",
+    conversation_extension = 5, # Randomnly combines conversations into 1
+    output_column_name = "label",
+)
+
+from unsloth import standardize_sharegpt
+dataset = standardize_sharegpt(dataset)
+
+chat_template = """{SYSTEM}
+USER: {INPUT}
+ASSISTANT: {OUTPUT}"""
+
+from unsloth import apply_chat_template
+dataset = apply_chat_template(
+    dataset,
+    tokenizer = tokenizer,
+    chat_template = chat_template,
+    default_system_message = "NER Task: Label the text based on the available Labels."
+)
+```
+
+## Training Configuration
+```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 = True, # Can make training 5x faster for short sequences.
+    args = TrainingArguments(
+        per_device_train_batch_size = 2,
+        gradient_accumulation_steps = 4,
+        warmup_steps = 5,
+        # max_steps = None,
+        num_train_epochs = 1,
+        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",
+    ),
+)
+
+trainer_stats = trainer.train()
+
+# Save to 8bit Q8_0
+if False: model.save_pretrained_gguf("model", tokenizer,)
+```
+
+## Training Results
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/678fa336b0c8266724597a95/hcRhMrr2lC5f2b9enD_1z.png)
+- Steps Trained: 26
+- Final Loss: 0.1870
+- Total Time: 21:04 min
+- Full epoch had been 261 steps
+
+# Sample Inference
+```python
+FastLanguageModel.for_inference(model) # Enable native 2x faster inference
+messages = [                    # Change below!
+    {"role": "user", "content": 'Labels: ATTR, CITY, CITY_PART, COUNTRY, O, ORG, PER, PHONE, REGION, REL, STREET, WORK_P, WORK_S\n\n'\
+                                'Text: "doctors in berlin"'},
+]
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt = True,
+    return_tensors = "pt",
+).to("cuda")
+
+from transformers import TextStreamer
+text_streamer = TextStreamer(tokenizer, skip_prompt = True)
+_ = model.generate(input_ids, streamer = text_streamer, max_new_tokens = 128, pad_token_id = tokenizer.eos_token_id)
+```
+
+