Instructions to use Phind/Phind-CodeLlama-34B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phind/Phind-CodeLlama-34B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Phind/Phind-CodeLlama-34B-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Phind/Phind-CodeLlama-34B-v1")
model = AutoModelForCausalLM.from_pretrained("Phind/Phind-CodeLlama-34B-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Phind/Phind-CodeLlama-34B-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Phind/Phind-CodeLlama-34B-v1

SGLang

How to use Phind/Phind-CodeLlama-34B-v1 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 "Phind/Phind-CodeLlama-34B-v1" \
    --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": "Phind/Phind-CodeLlama-34B-v1",
		"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 "Phind/Phind-CodeLlama-34B-v1" \
        --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": "Phind/Phind-CodeLlama-34B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Phind/Phind-CodeLlama-34B-v1 with Docker Model Runner:
```
docker model run hf.co/Phind/Phind-CodeLlama-34B-v1
```

michaelroyzen commited on Aug 28, 2023

Commit

32699c5

1 Parent(s): 5628b57

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -17,7 +17,10 @@ tags:
 - code llama
 ---
-# **Phind-CodeLlama-34B-v1**
 We've fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset that achieve 67.6% and 69.5% pass@1 on HumanEval, respectively. GPT-4 achieves 67%. We've applied OpenAI's decontamination methodology to our dataset to ensure result validity.
 More details can be found on our [blog post](https://www.phind.com/blog/code-llama-beats-gpt4).

 - code llama
 ---
+# NOTE: We've now launched **Phind-CodeLlama-34B-v2**, which acheives **73.8% pass@1** on HumanEval. It is instruction-tuned and much easier to use than this v1 model.
+# Check out Phind-CodeLlama-34B-v2 [here](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2).
+## **Phind-CodeLlama-34B-v1**
 We've fine-tuned CodeLlama-34B and CodeLlama-34B-Python on an internal Phind dataset that achieve 67.6% and 69.5% pass@1 on HumanEval, respectively. GPT-4 achieves 67%. We've applied OpenAI's decontamination methodology to our dataset to ensure result validity.
 More details can be found on our [blog post](https://www.phind.com/blog/code-llama-beats-gpt4).