Downloads · 30 days
18
82% of all-time downloads
sft_v0
thysics/sft_v0
sft_v0 is a text generation model from thysics. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
22
Public
Repo size
580 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors43.7 MB · 73%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Dec 8, 2025
- Updated
- Dec 9, 2025
- SHA
- 848ddf32
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
sft_v0
This model is a fine-tuned version of Qwen/Qwen3-8B on the swe_smith_mini dataset.
Model description
More information needed
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: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 8
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
Framework versions
- PEFT 0.17.1
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Dec 8, 2025
- Updated
- Dec 9, 2025