KUETLLM_zephyr

KUETLLM is a zephyr7b-beta finetune, using a dataset with prompts and answers about Khulna University of Engineering and Technology. It was loaded in 8 bit quantization using bitsandbytes. LORA was used to finetune an adapter, which was leter merged with the base unquantized model.

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

KUETLLM_zephyr

This model is a fine-tuned version of TheBloke/zephyr-7B-beta-GPTQ on the None dataset.

Model description

Below is the training configuarations for the finetuning process:

LoraConfig:
r=16,
lora_alpha=16,
target_modules=["q_proj", "v_proj","k_proj","o_proj","gate_proj","up_proj","down_proj"],
lora_dropout=0.05,
bias="none",
task_type="CAUSAL_LM"

TrainingArguments:
per_device_train_batch_size=12,
gradient_accumulation_steps=1,
optim='paged_adamw_8bit',
learning_rate=5e-06 ,
fp16=True,            
logging_steps=10,
num_train_epochs = 1,
output_dir=zephyr_lora_output,
remove_unused_columns=False,

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 24
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 96
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Inference

def process_data_sample(example):
    processed_example = "<|system|>\nYou are a KUET authority managed chatbot, help users by answering their queries about KUET.\n<|user|>\n" + example + "\n<|assistant|>\n"
    return processed_example

inp_str = process_data_sample("Tell me about KUET.")
inputs = tokenizer(inp_str, return_tensors="pt")
generation_config = GenerationConfig(
    do_sample=True,
    top_k=1,
    temperature=0.1,
    max_new_tokens=256,
    pad_token_id=tokenizer.eos_token_id
)

outputs = model.generate(**inputs, generation_config=generation_config)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0