Instructions to use drusepth/bloomp-blacksmith with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drusepth/bloomp-blacksmith with Transformers:

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

pipe = pipeline("text-generation", model="drusepth/bloomp-blacksmith")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("drusepth/bloomp-blacksmith")
model = AutoModelForCausalLM.from_pretrained("drusepth/bloomp-blacksmith", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use drusepth/bloomp-blacksmith with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drusepth/bloomp-blacksmith"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drusepth/bloomp-blacksmith",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/drusepth/bloomp-blacksmith

SGLang

How to use drusepth/bloomp-blacksmith 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 "drusepth/bloomp-blacksmith" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drusepth/bloomp-blacksmith",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "drusepth/bloomp-blacksmith" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drusepth/bloomp-blacksmith",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use drusepth/bloomp-blacksmith with Docker Model Runner:
```
docker model run hf.co/drusepth/bloomp-blacksmith
```

bloomp-blacksmith

Commit History

Feb 4, 2025

22:44
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
f047b44

Jan 12, 2023

23:16
include tokenizer config from bloom

drusepth

9c0ca3b
21:43
Upload BloomForCausalLM

drusepth

146683e
21:42
initial commit

drusepth

4cbf105

Commit History

Feb 4, 2025

Adding `safetensors` variant of this model⁠

Jan 12, 2023

include tokenizer config from bloom

Upload BloomForCausalLM

initial commit