Instructions to use bespokelabs/Bespoke-Stratos-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bespokelabs/Bespoke-Stratos-7B with Transformers:

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

pipe = pipeline("text-generation", model="bespokelabs/Bespoke-Stratos-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bespokelabs/Bespoke-Stratos-7B")
model = AutoModelForCausalLM.from_pretrained("bespokelabs/Bespoke-Stratos-7B", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bespokelabs/Bespoke-Stratos-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bespokelabs/Bespoke-Stratos-7B"
# 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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bespokelabs/Bespoke-Stratos-7B

SGLang

How to use bespokelabs/Bespoke-Stratos-7B 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-7B" \
    --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-7B",
		"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-7B" \
        --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-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bespokelabs/Bespoke-Stratos-7B with Docker Model Runner:
```
docker model run hf.co/bespokelabs/Bespoke-Stratos-7B
```

ryanmarten commited on Jan 22, 2025

Commit

962647b

verified ·

1 Parent(s): cf1601b

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -5

README.md CHANGED Viewed

@@ -24,12 +24,16 @@ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://hugging
 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](https://huggingface.co/datasets/Bespoke-Stratos-17k).
 It outperforms Qwen-2.5-7B-Instruct on math reasoning benchmarks:
-||Bespoke-Stratos-7B|DeepSeek-R1-Distill-Qwen-7B|Qwen2.5-7B-Instruct|
 |---|---|---|---|
-|AIME2024|20.0|55.5|10.0|
-|MATH500|82.0|83.3|74.2|
-|GPQA-Diamond|37.8|49.1|33.3|
-|LiveCodeBench|32.5|37.6|32.9|
 Note that the authors of Sky-T1 had [noted](https://github.com/NovaSky-AI/SkyThought/issues/4#issuecomment-2585860004) that they saw little or no improvement in training 7B or 14B models with their data.
 However, see an improvement, though not at the scale of DeepSeek's distilled model. The reason could be that we used 17k examples, while DeepSeek seems to have used 800k.

 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](https://huggingface.co/datasets/Bespoke-Stratos-17k).
 It outperforms Qwen-2.5-7B-Instruct on math reasoning benchmarks:
+||Bespoke-Stratos-7B|Qwen2.5-7B-Instruct|DeepSeek-R1-Distill-Qwen-7B|
 |---|---|---|---|
+|AIME2024|20.0|10.0|55.5|
+|MATH500|82.0|74.2|83.3|
+|GPQA-Diamond|37.8|33.3|49.1|
+|LiveCodeBench v2 Easy|71.4|65.9|81.3|
+|LiveCodeBench v2 Medium|25.5|18.9|42.2|
+|LiveCodeBench v2 Hard|1.6|3.3|2.4|
+|LiveCodeBench v2 All|36.1|31.9|46.6|
 Note that the authors of Sky-T1 had [noted](https://github.com/NovaSky-AI/SkyThought/issues/4#issuecomment-2585860004) that they saw little or no improvement in training 7B or 14B models with their data.
 However, see an improvement, though not at the scale of DeepSeek's distilled model. The reason could be that we used 17k examples, while DeepSeek seems to have used 800k.