import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, GemmaTokenizer

# download the file or use the HF_Token to get the model
model_id = file
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})

text = "sociological imagination is "
device = "cuda:0"
inputs = tokenizer(text, return_tensors="pt").to(device)

outputs = model.generate(**inputs, max_new_tokens=60)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

# Output: sociological imagination is <strong>the ability to see the relationship between personal troubles and public issues

Intended uses & limitations

More information needed

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: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
training_steps: 10
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.8.2
Transformers 4.38.1
Pytorch 2.3.1+cu121
Datasets 2.17.0
Tokenizers 0.15.2

cocaho/outputs

outputs

Model description

Example

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

cocaho/
outputs