metadata
license: mit
tags:
- causal_lm
- generated_from_trainer
base_model: broadfield-dev/gemma-3-270m-tuned-0102-0441
datasets:
- broadfield-dev/abisee_cnn_dailymail_concise-Broadfield
model-index:
- name: gemma-3-270m-tuned-0102-0441-tuned-0102-1157
results: []
gemma-3-270m-tuned-0102-0441-tuned-0102-1157
This model is a fine-tuned version of broadfield-dev/gemma-3-270m-tuned-0102-0441 on the broadfield-dev/abisee_cnn_dailymail_concise-Broadfield dataset.
Training Details
- Task: CAUSAL_LM
- Epochs: 1
- Learning Rate: 2e-05
- Gradient Accumulation Steps: 4
Entity Labels
['LABEL_0', 'LABEL_1']
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "broadfield-dev/gemma-3-270m-tuned-0102-0441-tuned-0102-1157"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16)
messages = [
{"role": "system", "content": "Summarize this: "},
{"role": "user", "content": "Your input here..."}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))