Downloads · 30 days
4
7% of all-time downloads
Anurich/meta-Llama-3.1-gpro-law-and-order
meta-Llama-3.1-gpro-law-and-order is a text generation model from Anurich. Use it when you need the model to write or continue text. It is set up for transformers.
We fine-tuned LLaMA-3.1-8B for 250 steps using GPRO to enhance its reasoning capabilities on the lawandorder dataset available on Hugging Face.
Downloads · 30 days
4
7% of all-time downloads
All-time downloads
59
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
We fine-tuned LLaMA-3.1-8B for 250 steps using GPRO to enhance its reasoning capabilities on the law_and_order dataset available on Hugging Face.
This model was trained on the law_and_order dataset and fine-tuned with GPRO to develop strong reasoning abilities. The fine-tuning process enables the model to analyze legal and procedural scenarios more effectively.
text = tokenizer.apply_chat_template([
{"role" : "system", "content" : SYSTEM_PROMPT},
{"role" : "user", "content" : "Different Cyber law in India?"},
], tokenize = False, add_generation_prompt = True)
from vllm import SamplingParams
sampling_params = SamplingParams(
temperature = 0.8,
top_p = 0.95,
max_tokens = 1024,
)
output = model.fast_generate(
text,
sampling_params = sampling_params,
lora_request = model.load_lora("grpo_saved_lora"),
)[0].outputs[0].text