bespokelabs / Bespoke-Stratos-32B

huggingface.co
Total runs: 124
24-hour runs: 2
7-day runs: 11
30-day runs: 75
Model's Last Updated: January 24 2025
text-generation

Introduction of Bespoke-Stratos-32B

Model Details of Bespoke-Stratos-32B

Model description

This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the Bespoke-Stratos-17k dataset . The dataset is derived by distilling DeepSeek-R1 using the data pipeline of Berkeley NovaSky’s Sky-T1 with some modifications. More info in the dataset card at Bespoke-Stratos-17k . It outperforms Qwen-2.5-32B-Instruct on reasoning benchmarks:

Metric Bespoke-Stratos-32B Sky-T1-32B o1-preview DeepSeek-R1 DeepSeek-R1-Distill-Qwen-32B (Ours) DeepSeek-R1-Distill-Qwen-32B (Reported)
AIME2024 63.3 43.3 40.0 79.8 66.7 72.6
MATH500 93.0 82.4 81.4 97.3 89.8 94.3
GPQA-Diamond 58.1 56.8 75.2 71.5 61.1 62.1
LCB v2 Easy 96.7 86.3 92.9 - 91.2 -
LCB v2 Medium 75.2 56.8 54.9 - 75.7 -
LCB v2 Hard 26.2 17.9 16.3 - 38.2 -
LCB v2 All 71.1 57.9 59.1 - 72.2 -
Intended uses & limitations

Apache 2.0 License

Training procedure

We used 8xH100 to train the model for 27 hours.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 12
  • total_train_batch_size: 96
  • total_eval_batch_size: 64
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0
Training results
Framework versions
  • Transformers 4.46.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.3

Runs of bespokelabs Bespoke-Stratos-32B on huggingface.co

124
Total runs
2
24-hour runs
5
3-day runs
11
7-day runs
75
30-day runs

More Information About Bespoke-Stratos-32B huggingface.co Model

More Bespoke-Stratos-32B license Visit here:

https://choosealicense.com/licenses/apache-2.0

Bespoke-Stratos-32B huggingface.co

Bespoke-Stratos-32B huggingface.co is an AI model on huggingface.co that provides Bespoke-Stratos-32B's model effect (), which can be used instantly with this bespokelabs Bespoke-Stratos-32B model. huggingface.co supports a free trial of the Bespoke-Stratos-32B model, and also provides paid use of the Bespoke-Stratos-32B. Support call Bespoke-Stratos-32B model through api, including Node.js, Python, http.

Bespoke-Stratos-32B huggingface.co Url

https://huggingface.co/bespokelabs/Bespoke-Stratos-32B

bespokelabs Bespoke-Stratos-32B online free

Bespoke-Stratos-32B huggingface.co is an online trial and call api platform, which integrates Bespoke-Stratos-32B's modeling effects, including api services, and provides a free online trial of Bespoke-Stratos-32B, you can try Bespoke-Stratos-32B online for free by clicking the link below.

bespokelabs Bespoke-Stratos-32B online free url in huggingface.co:

https://huggingface.co/bespokelabs/Bespoke-Stratos-32B

Bespoke-Stratos-32B install

Bespoke-Stratos-32B is an open source model from GitHub that offers a free installation service, and any user can find Bespoke-Stratos-32B on GitHub to install. At the same time, huggingface.co provides the effect of Bespoke-Stratos-32B install, users can directly use Bespoke-Stratos-32B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Bespoke-Stratos-32B install url in huggingface.co:

https://huggingface.co/bespokelabs/Bespoke-Stratos-32B

Url of Bespoke-Stratos-32B

Bespoke-Stratos-32B huggingface.co Url

Provider of Bespoke-Stratos-32B huggingface.co

bespokelabs
ORGANIZATIONS

Other API from bespokelabs