Instructions to use bespokelabs/Bespoke-Stratos-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bespokelabs/Bespoke-Stratos-32B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bespokelabs/Bespoke-Stratos-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bespokelabs/Bespoke-Stratos-32B")
model = AutoModelForCausalLM.from_pretrained("bespokelabs/Bespoke-Stratos-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bespokelabs/Bespoke-Stratos-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bespokelabs/Bespoke-Stratos-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bespokelabs/Bespoke-Stratos-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bespokelabs/Bespoke-Stratos-32B

SGLang

How to use bespokelabs/Bespoke-Stratos-32B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bespokelabs/Bespoke-Stratos-32B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bespokelabs/Bespoke-Stratos-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bespokelabs/Bespoke-Stratos-32B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bespokelabs/Bespoke-Stratos-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bespokelabs/Bespoke-Stratos-32B with Docker Model Runner:
```
docker model run hf.co/bespokelabs/Bespoke-Stratos-32B
```

Bespoke-Stratos-32B / README.md

ryanmarten

Update README.md

d96f794 verified over 1 year ago

preview code

raw

history blame contribute delete

2.24 kB

metadata

library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-32B-Instruct
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: original
    results: []
language:
  - en
datasets:
  - bespokelabs/Bespoke-Stratos-17k

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 // 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