Instructions to use rustformers/bloomz-ggml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rustformers/bloomz-ggml with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rustformers/bloomz-ggml")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rustformers/bloomz-ggml", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rustformers/bloomz-ggml with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rustformers/bloomz-ggml" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rustformers/bloomz-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rustformers/bloomz-ggml
- SGLang
How to use rustformers/bloomz-ggml 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 "rustformers/bloomz-ggml" \ --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": "rustformers/bloomz-ggml", "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 "rustformers/bloomz-ggml" \ --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": "rustformers/bloomz-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rustformers/bloomz-ggml with Docker Model Runner:
docker model run hf.co/rustformers/bloomz-ggml
Upload new model file: 'bloomz-560m-q5_1.bin'
Browse files- bloomz-560m-q5_1.bin +3 -0
- bloomz-560m-q5_1.meta +9 -0
bloomz-560m-q5_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34236298d30083e9d4f126bc9f0eeb1ddf86b9a697e6d01217a63b3d747f1f2a
|
| 3 |
+
size 616344875
|
bloomz-560m-q5_1.meta
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "Bloom",
|
| 3 |
+
"quantization": "Q5_1",
|
| 4 |
+
"quantization_version": "V2",
|
| 5 |
+
"container": "GGML",
|
| 6 |
+
"converter": "llm-rs",
|
| 7 |
+
"hash": "722f008e92145129e7c0354dcef259452e4e5fa35de619ae48f3bcbd7249be93",
|
| 8 |
+
"base_model": "bigscience/bloomz-560m"
|
| 9 |
+
}
|