Instructions to use budecosystem/code-millenials-34b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use budecosystem/code-millenials-34b with Transformers:

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

pipe = pipeline("text-generation", model="budecosystem/code-millenials-34b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("budecosystem/code-millenials-34b")
model = AutoModelForCausalLM.from_pretrained("budecosystem/code-millenials-34b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use budecosystem/code-millenials-34b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/budecosystem/code-millenials-34b

SGLang

How to use budecosystem/code-millenials-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 "budecosystem/code-millenials-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": "budecosystem/code-millenials-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 "budecosystem/code-millenials-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": "budecosystem/code-millenials-34b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use budecosystem/code-millenials-34b with Docker Model Runner:
```
docker model run hf.co/budecosystem/code-millenials-34b
```

Could you please confirm prompt template?

by KrisPi - opened Jan 12, 2024

Discussion

KrisPi

Jan 12, 2024

Does the prompt template is supposed to have one new line sign after system prompt and then only spaces? In case of multiturn conversation do you expect new line after each turn?

dittops

Bud org Jan 13, 2024

There should be new lines after the system prompt and also after each turn. Please refer this https://github.com/BudEcosystem/code-millenials/blob/main/utils/prompt.py. You can change the system prompt as needed

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment