Downloads · 30 days
5
17% of all-time downloads
paster0823/m4ore-sport-slm-llama3.1-finetune
m4ore-sport-slm-llama3.1-finetune is a machine learning model from paster0823. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
⚠️ 重要聲明 / Important Notice 本模型是基於 Llama-3.1-TAIDE-LX-8B-Chat 進行微調的衍生模型。 This model is a derivative work based on Llama-3.1-TAIDE-LX-8B-Chat.
Downloads · 30 days
5
17% of all-time downloads
All-time downloads
30
Public
Parameters
8.5B
17.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17 GB · 100%
From the Hugging Face model README
⚠️ 重要聲明 / Important Notice 本模型是基於 Llama-3.1-TAIDE-LX-8B-Chat 進行微調的衍生模型。 This model is a derivative work based on Llama-3.1-TAIDE-LX-8B-Chat.
This model is a full parameter fine-tuned version of Llama-3.1-TAIDE-LX-8B-Chat specialized for sports and fitness-related question answering and text generation.
This model is designed for:
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "paster0823/m4ore-sport-slm-llama3.1-finetune"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto"
)
# Example prompt
prompt = "請問跑步前應該做什麼熱身運動?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=512,
temperature=0.7,
top_p=0.9,
do_sample=True
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
This model is released under the Llama-3.1-TAIDE Models License Agreement, which is based on:
Important License Requirements:
Full License:
Governing Law: Republic of China (Taiwan) law applies to this license.
If you use this model, please cite:
@misc{m4ore-sport-llama3.1,
title={M4ore Sport Llama 3.1 Fine-tune},
author={M4ore Team},
year={2025},
howpublished={\url{https://huggingface.co/paster0823/m4ore-sport-slm-llama3.1-finetune}}
}
This model is built upon: