Instructions to use amazon/GDN-primed-HQwen3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amazon/GDN-primed-HQwen3-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="amazon/GDN-primed-HQwen3-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("amazon/GDN-primed-HQwen3-8B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amazon/GDN-primed-HQwen3-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amazon/GDN-primed-HQwen3-8B-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": "amazon/GDN-primed-HQwen3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amazon/GDN-primed-HQwen3-8B-Instruct

SGLang

How to use amazon/GDN-primed-HQwen3-8B-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 "amazon/GDN-primed-HQwen3-8B-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": "amazon/GDN-primed-HQwen3-8B-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 "amazon/GDN-primed-HQwen3-8B-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": "amazon/GDN-primed-HQwen3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amazon/GDN-primed-HQwen3-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/amazon/GDN-primed-HQwen3-8B-Instruct
```

benbowman314 commited on 5 days ago

Commit

9b48959

1 Parent(s): 4324333

Updated model card to add caveat regarding tool-calling capabilities

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -54,11 +54,11 @@ Increasing hybridization ratio, replacing more Attention layers with SSM layers,
 - **License**: Apache 2.0
-Note, this is an Instruct-tuned model and is not a thinking model, that is, it does not natively produce chain-of-thought thinking tokens in its generation trace.
 ## Benchmark Results
-Below we report benchmark performance for all our instruct-tuned Primed models. All Hybrid models use a 50% Hybrid ratio and are Primed from Qwen3-8B.
 We consider two baselines:

 - **License**: Apache 2.0
+Note, this is an Instruction-tuned model and is not a thinking model, that is, it does not natively produce chain-of-thought thinking tokens in its generation trace.  Tool calling is not supported by this checkpoint.  If you need tool calling capabilities, use the Reasoner checkpoints.
 ## Benchmark Results
+Below we report benchmark performance for all our instruction-tuned Primed models. All Hybrid models use a 50% Hybrid ratio and are Primed from Qwen3-8B.
 We consider two baselines: