Downloads · 30 days
27
51% of all-time downloads
Qwen2.5-7B
Nin8520/Qwen2.5-7B
Qwen2.5-7B is a text generation model from Nin8520. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
53
Public
Parameters
7.6B
30.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Mar 30, 2025
- Updated
- Apr 3, 2025
- SHA
- 8ca8e1c7
Base models
Model card
From the Hugging Face model README
Model Details
- Base Model: Qwen2.5-7B-Instruct
Training Details
Training Data
Training Setting
args = dict(
stage="sft",
do_train=True,
model_name_or_path="Qwen/Qwen2.5-7B-Instruct",
dataset="yue_1,yue_2",
template="alpaca",
finetuning_type="lora",
lora_target="all",
output_dir="Qwen2.5_lora",
per_device_train_batch_size=2,
gradient_accumulation_steps=4,
lr_scheduler_type="cosine",
logging_steps=5,
warmup_ratio=0.1,
save_steps=1000,
learning_rate=5e-5,
num_train_epochs=1.0,
max_samples=300,
max_grad_norm=1.0,
loraplus_lr_ratio=16.0,
fp16=True,
report_to="none",
)
Evaluation
Not done
<!-- This section describes the evaluation protocols and provides the results. -->- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Languages
- zh, en
- Created
- Mar 30, 2025
- Updated
- Apr 3, 2025