53d79be8bd
Model: laion/openthoughts-4-code-qwen3-32b-annotated-7k_qwen3-1.7B_10k Source: Original Platform
1.4 KiB
1.4 KiB
library_name, license, base_model, tags, model-index
| library_name | license | base_model | tags | model-index | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| transformers | other | Qwen/Qwen3-1.7B |
|
|
Openthoughts-4-code-qwen3-32b-annotated-7k_qwen3-1.7B_10k
This model is a fine-tuned version of Qwen3-1.7B, 10k output length, on the laion/openthoughts-4-code-qwen3-32b-7k-annotated-sharegpt dataset (which is created using https://huggingface.co/datasets/mlfoundations-dev/hero_run_4_code as seed for generation, Qwen3 32B with 7.5k output length)
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: 0.0002
- per_device_train_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 256
- total_train_batch_size: 1024
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8.0
Training results
Framework versions
- Transformers 4.55.0
- Pytorch 2.7.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1