Update README.md

README.md

@@ -37,8 +37,8 @@ Once it's installed, we can import the necessary libraries and log in to W&B (op
 
 """
 wandb
-https://wandb.ai/aliforootani-UFZ
-you need wb_token
+https://wandb.ai/wandb_account
+you need wb_token as well
 """
 
 import gc
@@ -233,7 +233,180 @@ Training the model on these 1,000 samples and 20 epochs took about 22 hours on a
 
 
 
-### Model Description
+
+
+## Test the model
+
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Jul  3 15:57:22 2024
+
+@author: Ali forootani
+"""
+
+"""
+!pip install -U transformers datasets accelerate peft trl bitsandbytes wandb
+!pip install -qqq flash-attn
+!pip install -qU transformers accelerate
+"""
+
+"""
+wandb
+https://wandb.ai/your_account
+dde689e74d3f9146d2d116b098016f5e0d9cc202
+"""
+
+
+```python
+import gc
+import os
+
+import torch
+import wandb
+from datasets import load_dataset
+
+
+
+# Directly insert your Weights & Biases API key here
+wb_token = 'your_wb_token'
+wandb.login(key=wb_token)
+
+
+from peft import LoraConfig, PeftModel, prepare_model_for_kbit_training
+
+from transformers import (
+    AutoModelForCausalLM,
+    AutoTokenizer,
+    BitsAndBytesConfig,
+    TrainingArguments,
+    pipeline,)
+
+from trl import ORPOConfig, ORPOTrainer, setup_chat_format
+
+
+
+
+"""
+https://huggingface.co/blog/mlabonne/orpo-llama-3
+
+mlabonne/orpo-dpo-mix-40k
+
+https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k/tree/main
+"""
+
+if torch.cuda.get_device_capability()[0] >= 128:
+    
+    attn_implementation = "flash_attention_2"
+    torch_dtype = torch.bfloat16
+else:
+    attn_implementation = "eager"
+    torch_dtype = torch.float16
+
+
+##################################
+
+import sys
+import os
+
+cwd = os.getcwd()
+# sys.path.append(cwd + '/my_directory')
+sys.path.append(cwd)
+
+
+def setting_directory(depth):
+    current_dir = os.path.abspath(os.getcwd())
+    root_dir = current_dir
+    for i in range(depth):
+        root_dir = os.path.abspath(os.path.join(root_dir, os.pardir))
+        sys.path.append(os.path.dirname(root_dir))
+    return root_dir
+
+
+model_path = "/data/bio-eng-llm/llm_repo/mlabonne/OrpoLlama-3-8B"
+
+
+###################################
+###################################
+
+"""
+# Model
+base_model = "meta-llama/Meta-Llama-3-8B"
+new_model = "OrpoLlama-3-8B"
+"""
+
+
+# QLoRA config
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype= torch_dtype,
+    bnb_4bit_use_double_quant=True,
+)
+
+# LoRA config
+peft_config = LoraConfig(
+    r=16,
+    lora_alpha=32,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=['up_proj', 'down_proj', 'gate_proj', 'k_proj', 'q_proj', 'v_proj', 'o_proj']
+)
+
+
+# Reload tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    low_cpu_mem_usage=True,
+    return_dict=True,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+model, tokenizer = setup_chat_format(model, tokenizer)
+
+
+
+root_dir = setting_directory(0)
+epochs = 20
+
+new_model_path = root_dir + f"models/fine_tuned_models/OrpoLlama-3-8B_{epochs}e_qa_qa"
+
+
+### Merge adapter with base model
+model = PeftModel.from_pretrained(model, new_model_path)
+model = model.merge_and_unload()
+
+print("#############################")
+print("#############################")
+print(model)
+
+
+
+
+# Pushing the model into the Huggingface hub
+
+from huggingface_hub import HfApi, login
+
+#########################################################
+#########################################################
+#########################################################
+######## Repo token
+# Login to Hugging Face
+login(token="your_huggingface_token")
+
+# Define your Hugging Face repository name
+repo_name = "your_name/OrpoLlama-3-8B_fine_tune_trl"
+
+
+
+# Push the model and tokenizer 2
+model.push_to_hub(repo_name, use_auth_token=True)
+tokenizer.push_to_hub(repo_name, use_auth_token=True)
+```
+
+
+
 
 <!-- Provide a longer summary of what this model is. -->