metadata
license: apache-2.0
language:
- bn
To run:
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16
)
config = {
'base_model_name_or_path': 'deepseek-ai/deepseek-math-7b-base'
}
PEFT_MODEL = "trained-model3"
config = PeftConfig.from_pretrained(PEFT_MODEL)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
return_dict=True,
quantization_config=bnb_config,
device_map="sequential",
trust_remote_code=True
)
tokenizer=AutoTokenizer.from_pretrained(config.base_model_name_or_path)
tokenizer.pad_token = tokenizer.eos_token
model = PeftModel.from_pretrained(model, PEFT_MODEL)
generation_config = model.generation_config
generation_config.max_new_tokens = 2048
generation_config.temperature = 0.7
generation_config.top_p = 0.7
generation_config.do_sample = True
generation_config.num_return_sequences = 1
generation_config.pad_token_id = tokenizer.eos_token_id
generation_config.eos_token_id = tokenizer.eos_token_id
prompt = f"""Problem Statement: {ques}"""
encoding = tokenizer(prompt, return_tensors="pt").to(device)
with torch.inference_mode():
outputs = model.generate(
input_ids = encoding.input_ids,
attention_mask = encoding.attention_mask,
generation_config = generation_config
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))