Instructions to use h2oai/h2o-danube3-500m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h2oai/h2o-danube3-500m-base with Transformers:

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

pipe = pipeline("text-generation", model="h2oai/h2o-danube3-500m-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h2oai/h2o-danube3-500m-base")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2o-danube3-500m-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use h2oai/h2o-danube3-500m-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h2oai/h2o-danube3-500m-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h2oai/h2o-danube3-500m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/h2oai/h2o-danube3-500m-base

SGLang

How to use h2oai/h2o-danube3-500m-base 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 "h2oai/h2o-danube3-500m-base" \
    --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": "h2oai/h2o-danube3-500m-base",
		"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 "h2oai/h2o-danube3-500m-base" \
        --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": "h2oai/h2o-danube3-500m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use h2oai/h2o-danube3-500m-base with Docker Model Runner:
```
docker model run hf.co/h2oai/h2o-danube3-500m-base
```

Xenova HF Staff commited on Jul 15, 2024

Commit

439a3f1

verified ·

1 Parent(s): 56620a2

Upload ONNX weights

Browse files

Files changed (8) hide show

onnx/model.onnx +3 -0
onnx/model_bnb4.onnx +3 -0
onnx/model_fp16.onnx +3 -0
onnx/model_int8.onnx +3 -0
onnx/model_q4.onnx +3 -0
onnx/model_q4f16.onnx +3 -0
onnx/model_quantized.onnx +3 -0
onnx/model_uint8.onnx +3 -0

onnx/model.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a41462fb935db8b516adf15e3fec6367dcc53940a2598b2a57ccdd3d23490f92
+size 2054884318

onnx/model_bnb4.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:972e6b765a3744c3dde50dc13fe2c4d64803394d9de984f50630c5ebd271c6a7
+size 525807745

onnx/model_fp16.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdb7e49df7d1df1684b92e6a50148da081aeec4651b9ada9909ff2f29214eec
+size 1094953534

onnx/model_int8.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:99d53d6b36cfa9cad7bbb6a79138e953cf85395077816affd9750a3020716619
+size 581626637

onnx/model_q4.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b62c037b963a1f54c2f287a7252e6cab559ce03ad391ad4d8e93d31c85f6ea93
+size 554831065

onnx/model_q4f16.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aae9e842e81e90ff2315c4b26e515d83f7d74db21445deba3e128fcf2a7659
+size 427423291

onnx/model_quantized.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:99d53d6b36cfa9cad7bbb6a79138e953cf85395077816affd9750a3020716619
+size 581626637

onnx/model_uint8.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5a558b185fe66f9cccf5cbec30644a086427c41591d4bcf7ebaf66df417595fc
+size 581626686