Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: True
• load_in_4bit: False
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: fp4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float32

Framework versions

• PEFT 0.6.0.dev0

Model Access

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

peft_model_id = "sayril007/opt_lora-7b-lora-pretrained" config = PeftConfig.from_pretrained(peft_model_id) model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto') tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

Load the Lora model

model = PeftModel.from_pretrained(model, peft_model_id)

batch = tokenizer("Two things are infinite: ", return_tensors='pt')

with torch.cuda.amp.autocast(): output_tokens = model.generate(**batch, max_new_tokens=50)

print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))