Instructions to use HCHs/RivetCoder-9B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HCHs/RivetCoder-9B-A4B with Transformers:

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

pipe = pipeline("text-generation", model="HCHs/RivetCoder-9B-A4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HCHs/RivetCoder-9B-A4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HCHs/RivetCoder-9B-A4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HCHs/RivetCoder-9B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HCHs/RivetCoder-9B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HCHs/RivetCoder-9B-A4B

SGLang

How to use HCHs/RivetCoder-9B-A4B 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 "HCHs/RivetCoder-9B-A4B" \
    --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": "HCHs/RivetCoder-9B-A4B",
		"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 "HCHs/RivetCoder-9B-A4B" \
        --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": "HCHs/RivetCoder-9B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HCHs/RivetCoder-9B-A4B with Docker Model Runner:
```
docker model run hf.co/HCHs/RivetCoder-9B-A4B
```

HCHs commited on 3 days ago

Commit

9a90b19

verified ·

1 Parent(s): 745106e

Correct packaging note and refresh checksums

Browse files

Files changed (2) hide show

UPLOAD_INSTRUCTIONS.md +3 -3
provenance/checksums.sha256 +1 -1

UPLOAD_INSTRUCTIONS.md CHANGED Viewed

@@ -34,6 +34,6 @@ hf download HCHs/RivetCoder-9B-A4B `
   --dry-run
 ```
-The local weight files are hardlinks to the verified source artifacts. They are
-ordinary files for upload purposes and remain valid even if one of the other
-hardlink paths is removed.

   --dry-run
 ```
+The nine final weight shards are standalone, physically de-duplicated files
+produced by the final repack step. They do not depend on the component-checkpoint
+paths used during assembly.

provenance/checksums.sha256 CHANGED Viewed

@@ -35,4 +35,4 @@ ec7558e18405570c051065b40d0811fe5635fca0b057825b0c9be3490846f676  README.md
 ee1fa8fc1ed52ab1944fc4b65db3e5eae74e98a92bf0ee6f54dbd5f86daeb4b4  requirements.txt
 695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41  tokenizer.json
 11f1de897317b489dd09199284528382eeb17f566398b16e2039bb2266d26b09  tokenizer_config.json
-01d21bd5d0a74757cf1559dec0d7036728b532ed4e337bdb0f5f3bb1182d8036  UPLOAD_INSTRUCTIONS.md

 ee1fa8fc1ed52ab1944fc4b65db3e5eae74e98a92bf0ee6f54dbd5f86daeb4b4  requirements.txt
 695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41  tokenizer.json
 11f1de897317b489dd09199284528382eeb17f566398b16e2039bb2266d26b09  tokenizer_config.json
+2adc48a1d558261d69de8f43f35d8b3dc19bf122b604038cc8c56e5eadaf972c  UPLOAD_INSTRUCTIONS.md