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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BallisticAI/Ballistic-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": "BallisticAI/Ballistic-CodeLlama-34B-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

Ballistic-CodeLlama-34B-v1 / README.md

BallisticAI

Update README.md

e35f28e over 2 years ago

preview code

raw

history blame contribute delete

2.31 kB

	---
	license: llama2
	tags:
	- code llama
	base_model: BallisticAI/Ballistic-CodeLlama-34B-v1
	inference: false
	model_creator: BallisticAI
	model_type: llama
	prompt_template: '### System Prompt

	{system_message}


	### User Message

	{prompt}


	### Assistant

	'
	quantized_by: BallisticAI
	model-index:
	- name: Ballistic-CodeLlama-34B-v1
	results:
	- task:
	type: text-generation
	dataset:
	name: HumanEval
	type: openai_humaneval
	metrics:
	- type: n/a
	value: n/a
	name: n/a
	verified: false
	---



	# CodeLlama 34B v1
	- Model creator: [BallisticAI](https://huggingface.co/BallisticAI)
	- Based on: [CodeLlama 34B hf](https://huggingface.co/codellama/CodeLlama-34b-hf)
	- Merged with: [CodeLlama 34B v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2) && [speechless-codellama-34b-v2](https://huggingface.co/uukuguy/speechless-codellama-34b-v2.0)
	- Additional training with: [jondurbin/airoboros-2.2](https://huggingface.co/datasets/jondurbin/airoboros-2.2)


	<!-- description start -->
	## Description

	This repo contains model for [Ballistic-CodeLlama-34B-v1](https://huggingface.co/BallisticAI/Ballistic-CodeLlama-34B-v1).

	<!-- description end -->

	<!-- repositories-available start -->
	## Repositories available

	* [AWQ model for GPU inference.](https://huggingface.co/BallisticAI/Ballistic-CodeLlama-34B-v1-AWQ)
	* [GGUF model for CPU inference.](https://huggingface.co/BallisticAI/Ballistic-CodeLlama-34B-v1-GGUF)
	<!-- repositories-available end -->


	<!-- prompt-template start -->
	## How to Prompt the Model
	This model accepts the Alpaca/Vicuna instruction format.

	For example:

	```
	### System Prompt
	You are an intelligent programming assistant.

	### User Message
	Implement a linked list in C++

	### Assistant
	...
	```

	<!-- prompt-template end -->


	## Bias, Risks, and Limitations

	<!-- This section is meant to convey both technical and sociotechnical limitations. -->
	This model has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.



	## Thanks

	Thanks to:

	- The Original Llama team
	- [Phind](https://huggingface.co/phind)
	- [uukuguy](https://huggingface.co/uukuguy)
	- [jondurbin](https://huggingface.co/jondurbin)
	- And everyone else who's involved in the Open Source AI/ML Community.