Instructions to use Harryxun/llama32-code-ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harryxun/llama32-code-ds with Transformers:

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

pipe = pipeline("text-generation", model="Harryxun/llama32-code-ds")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harryxun/llama32-code-ds")
model = AutoModelForCausalLM.from_pretrained("Harryxun/llama32-code-ds", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Harryxun/llama32-code-ds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harryxun/llama32-code-ds"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harryxun/llama32-code-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Harryxun/llama32-code-ds

SGLang

How to use Harryxun/llama32-code-ds 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 "Harryxun/llama32-code-ds" \
    --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": "Harryxun/llama32-code-ds",
		"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 "Harryxun/llama32-code-ds" \
        --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": "Harryxun/llama32-code-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Harryxun/llama32-code-ds with Docker Model Runner:
```
docker model run hf.co/Harryxun/llama32-code-ds
```

Harryxun commited on Nov 11, 2025

Commit

8b663a3

verified ·

1 Parent(s): f077261

Training in progress, step 5000

Browse files

Files changed (3) hide show

model.safetensors +1 -1
tokenizer.json +2 -2
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c7a82f5157ad3bfe473f3ab7fe66b7ed688821cb8650c81a51decd401e46b2
 size 4943274328

 version https://git-lfs.github.com/spec/v1
+oid sha256:db7859dac6fc66ece6adac149051f92fb5479d16622778f624fb78a2975dd252
 size 4943274328

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e6b3307ed78e0b09fbe72512bbe09e95bb1c177d72e5db22786b3688e8dc429
-size 17210018

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a265d3a607c4eb61558668a1b61d04befc6e452f5164b6d61dc55ae4c038fb0
 size 5777

 version https://git-lfs.github.com/spec/v1
+oid sha256:c8f38bb79159969e3ec6a312f46b7048bb429e6fa286ed92fe19837925c13e09
 size 5777