RPBizkit-v4-12B_Lorablated

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, LoraConfig

# --- CONFIGURATION ---
base_model_path = "RicardoEstep/RPBizkit-v4-12B"
lora_path = "nbeerbower/Mistral-Nemo-12B-abliterated-LORA"
tokenizer_path = "yamatazen/EtherealAurora-12B"
output_path = "./RPBizkit-v4-12B-Abliterated-ChatML"

print("Loading base model...")
# We load without device_map="auto" initially to avoid naming issues with accelerate
model = AutoModelForCausalLM.from_pretrained(
    base_model_path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True
)

# 1. FIX THE VOCAB SIZE (The 131075 -> 131072 issue)
print(f"Resizing from {model.get_input_embeddings().weight.shape[0]} to 131072...")
model.resize_token_embeddings(131072)

# 2. APPLY THE LORA MANUALLY
print("Applying LoRA...")
# We use from_pretrained but specify the exact model to avoid double-nesting
model = PeftModel.from_pretrained(
    model, 
    lora_path,
    adapter_name="default"
)

# 3. MERGE THE WEIGHTS
print("Merging weights into base...")
model = model.merge_and_unload()

# 4. FIX THE TOKENIZER
print("Finalizing tokenizer...")
tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, trust_remote_code=True)

# 5. SAVE
model.save_pretrained(output_path)
tokenizer.save_pretrained(output_path)

print("Process Complete!")