Instructions to use rustformers/bloom-ggml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rustformers/bloom-ggml with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rustformers/bloom-ggml")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rustformers/bloom-ggml", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rustformers/bloom-ggml with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rustformers/bloom-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/bloom-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rustformers/bloom-ggml
- SGLang
How to use rustformers/bloom-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/bloom-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/bloom-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/bloom-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/bloom-ggml", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rustformers/bloom-ggml with Docker Model Runner:
docker model run hf.co/rustformers/bloom-ggml
Upload new model file: 'bloom-560m-q5_1-ggjt.bin'
Browse files- bloom-560m-q5_1-ggjt.bin +3 -0
- bloom-560m-q5_1-ggjt.meta +9 -0
bloom-560m-q5_1-ggjt.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6e102a3d7716c93db76a5c4182eb593213ad5c88f35eb288afeed3549cbd77e
|
| 3 |
+
size 617353184
|
bloom-560m-q5_1-ggjt.meta
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "Bloom",
|
| 3 |
+
"quantization": "Q5_1",
|
| 4 |
+
"quantization_version": "V2",
|
| 5 |
+
"container": "GGJT",
|
| 6 |
+
"converter": "llm-rs",
|
| 7 |
+
"hash": "ec6bd5ae06b0c5734e37c37bb0cefed2589183e558bfff2fb93956d6a72ece8e",
|
| 8 |
+
"base_model": "bigscience/bloom-560m"
|
| 9 |
+
}
|