Instructions to use patched-codes/patched-coder-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patched-codes/patched-coder-34b with Transformers:

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

pipe = pipeline("text-generation", model="patched-codes/patched-coder-34b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("patched-codes/patched-coder-34b")
model = AutoModelForCausalLM.from_pretrained("patched-codes/patched-coder-34b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use patched-codes/patched-coder-34b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "patched-codes/patched-coder-34b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patched-codes/patched-coder-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/patched-codes/patched-coder-34b

SGLang

How to use patched-codes/patched-coder-34b 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 "patched-codes/patched-coder-34b" \
    --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": "patched-codes/patched-coder-34b",
		"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 "patched-codes/patched-coder-34b" \
        --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": "patched-codes/patched-coder-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use patched-codes/patched-coder-34b with Docker Model Runner:
```
docker model run hf.co/patched-codes/patched-coder-34b
```

codelion commited on Oct 2, 2023

Commit

507ff2d

1 Parent(s): 93590d0

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -122,9 +122,9 @@ To evaluate the model for vulnerability remediation we used the `Static Analysis
 | Model | HumanEval | HumanEval Fix Python| Static Analysis Eval |
 | ----- | ----------| ------------------- | -------------------- |
-| GPT-4 | 86.6 | 47 | 55.26 |
 | patched-coder-34b | 53.57 | 41.34 | 51.32 |
 | CodeLlama-34b-Python | 53.29 | 33.14 | 27.63 |
 Based on the results on these benchmarks, patched-coder-34b is the SOTA open code LLM. Other code LLMs (e.g. from WizardCoder and Phind) are trained on
 either unknown proprietary datasets or used OpenAI's APIs for training, thus making them unviable for commercial use.

 | Model | HumanEval | HumanEval Fix Python| Static Analysis Eval |
 | ----- | ----------| ------------------- | -------------------- |
 | patched-coder-34b | 53.57 | 41.34 | 51.32 |
 | CodeLlama-34b-Python | 53.29 | 33.14 | 27.63 |
+| GPT-4 | 86.6 | 47 | 55.26 |
 Based on the results on these benchmarks, patched-coder-34b is the SOTA open code LLM. Other code LLMs (e.g. from WizardCoder and Phind) are trained on
 either unknown proprietary datasets or used OpenAI's APIs for training, thus making them unviable for commercial use.