Instructions to use nvidia/Hymba-1.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Hymba-1.5B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Hymba-1.5B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nvidia/Hymba-1.5B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nvidia/Hymba-1.5B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Hymba-1.5B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Hymba-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Hymba-1.5B-Instruct

SGLang

How to use nvidia/Hymba-1.5B-Instruct 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 "nvidia/Hymba-1.5B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Hymba-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "nvidia/Hymba-1.5B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Hymba-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Hymba-1.5B-Instruct with Docker Model Runner:
```
docker model run hf.co/nvidia/Hymba-1.5B-Instruct
```

YongganFu commited on Nov 1, 2024

Commit

d253bfd

verified ·

1 Parent(s): ac10307

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ Developed by Deep Learning Efficiency Research (DLER) team at NVIDIA Research.
 - Fuse attention heads and SSM heads within the same layer, offering parallel and complementary processing of the same inputs
 <div align="center">
-<img src="https://huggingface.co/nvidia/Hymba-1.5B/resolve/main/images/module.png" alt="Hymba Module" width="600">
 </div>
 - Introduce meta tokens that are prepended to the input sequences and interact with all subsequent tokens, thus storing important information and alleviating the burden of "forced-to-attend" in attention
@@ -20,7 +20,7 @@ Developed by Deep Learning Efficiency Research (DLER) team at NVIDIA Research.
 - Integrate with cross-layer KV sharing and global-local attention to further boost memory and computation efficiency
 <div align="center">
-<img src="https://huggingface.co/nvidia/Hymba-1.5B/resolve/main/images/macro_arch.png" alt="Hymba Model" width="600">
 </div>
@@ -32,7 +32,7 @@ Developed by Deep Learning Efficiency Research (DLER) team at NVIDIA Research.
 </div>
-- Hymba-1.5B-Instruct: Outperform all sub-2B public models.
 <div align="center">

 - Fuse attention heads and SSM heads within the same layer, offering parallel and complementary processing of the same inputs
 <div align="center">
+<img src="https://huggingface.co/nvidia/Hymba-1.5B-Instruct/resolve/main/images/module.png" alt="Hymba Module" width="600">
 </div>
 - Introduce meta tokens that are prepended to the input sequences and interact with all subsequent tokens, thus storing important information and alleviating the burden of "forced-to-attend" in attention
 - Integrate with cross-layer KV sharing and global-local attention to further boost memory and computation efficiency
 <div align="center">
+<img src="https://huggingface.co/nvidia/Hymba-1.5B-Instruct/resolve/main/images/macro_arch.png" alt="Hymba Model" width="600">
 </div>
 </div>
+- Hymba-1.5B-Instruct: Outperform SOTA small LMs.
 <div align="center">