|
--- |
|
license: mit |
|
base_model: TheBloke/zephyr-7B-beta-GPTQ |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: KUETLLM_zephyr |
|
results: [] |
|
--- |
|
KUETLLM is a [zephyr7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-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](https://github.com/TimDettmers/bitsandbytes). [LORA](https://huggingface.co/docs/diffusers/main/en/training/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](https://huggingface.co/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 |
|
|
