Instructions to use anudaw/distilled-code-llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anudaw/distilled-code-llama with Transformers:

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

pipe = pipeline("text-generation", model="anudaw/distilled-code-llama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anudaw/distilled-code-llama")
model = AutoModelForCausalLM.from_pretrained("anudaw/distilled-code-llama")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use anudaw/distilled-code-llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/anudaw/distilled-code-llama

SGLang

How to use anudaw/distilled-code-llama 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 "anudaw/distilled-code-llama" \
    --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": "anudaw/distilled-code-llama",
		"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 "anudaw/distilled-code-llama" \
        --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": "anudaw/distilled-code-llama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use anudaw/distilled-code-llama with Docker Model Runner:
```
docker model run hf.co/anudaw/distilled-code-llama
```

anudaw commited on Apr 30, 2024

Commit

7a3bcef

verified ·

1 Parent(s): af052f0

Training in progress, epoch 0

Browse files

Files changed (2) hide show

model.safetensors +1 -1
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a957e3aab893c20ecbfce924ac1e0ec5589b5ebc911b498ca7b8e269bea2a5ed
 size 2200119864

 version https://git-lfs.github.com/spec/v1
+oid sha256:4183242731eb78ea6b46057d5ae0ed72492b871c7fde5906e64348e88f3c6f70
 size 2200119864

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c105939d0c9592e48ef3ce2d32e4e676ad64d775a482362363c91f86d0858f
 size 4984

 version https://git-lfs.github.com/spec/v1
+oid sha256:649487f48aabe2a8d911cbe4db0a2d30105f0cca9cb51ad694e9b307676562f8
 size 4984