Instructions to use malteos/bloom-6b4-clp-german with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use malteos/bloom-6b4-clp-german with Transformers:

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

pipe = pipeline("text-generation", model="malteos/bloom-6b4-clp-german")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("malteos/bloom-6b4-clp-german", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use malteos/bloom-6b4-clp-german with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "malteos/bloom-6b4-clp-german"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "malteos/bloom-6b4-clp-german",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/malteos/bloom-6b4-clp-german

SGLang

How to use malteos/bloom-6b4-clp-german 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 "malteos/bloom-6b4-clp-german" \
    --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": "malteos/bloom-6b4-clp-german",
		"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 "malteos/bloom-6b4-clp-german" \
        --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": "malteos/bloom-6b4-clp-german",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use malteos/bloom-6b4-clp-german with Docker Model Runner:
```
docker model run hf.co/malteos/bloom-6b4-clp-german
```

malteos

Wauplin HF Staff commited on Apr 15, 2023

Commit

15fda87

1 Parent(s): 26cbbfb

Add ggml-model-bloom-6b4-clp-german-f16.bin from bloomz.cpp converter. (#2)

Browse files

- Upload ggml-model-bloom-6b4-clp-german-f16.bin with huggingface_hub (6b3f5dcea5542cca54a5eb5cc7001777fb7a7831)
- Upload README.md with huggingface_hub (778daf00348482fa5886c598a146c58143c72440)

Co-authored-by: Lucain Pouget <Wauplin@users.noreply.huggingface.co>

Files changed (2) hide show

README.md +6 -3
ggml-model-bloom-6b4-clp-german-f16.bin +3 -0

README.md CHANGED Viewed

@@ -1,10 +1,13 @@
 ---
-license: bigscience-bloom-rail-1.0
-datasets:
-- oscar
 language:
 - de
 library_name: transformers
 pipeline_tag: text-generation
 ---

 ---
 language:
 - de
+license: bigscience-bloom-rail-1.0
 library_name: transformers
+tags:
+- ggml
+- bloom
+datasets:
+- oscar
 pipeline_tag: text-generation
 ---

ggml-model-bloom-6b4-clp-german-f16.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:146486c1d479c09ecf608bdacc88c30c7c086532fee0cb1e8b6034b027fa52ed
+size 12910813184