Downloads · 30 days
9
2% of all-time downloads
mix760_3step_bc760
jiayicheng/mix760_3step_bc760
mix760_3step_bc760 is a text generation model from jiayicheng. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
390
Public
Parameters
308K
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- qwen3
- Access
- Public
- Created
- May 7, 2026
- Updated
- May 7, 2026
- SHA
- 5b038cea
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. -->
train_output
This model is a fine-tuned version of Qwen/Qwen3-8B on the sft_mixed760_official760 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: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- total_eval_batch_size: 32
- 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: 7.0
Training results
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.1
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- other
- Created
- May 7, 2026
- Updated
- May 7, 2026