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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

CodeLlama 34B v1

Model creator: BallisticAI
Based on: CodeLlama 34B hf
Merged with: CodeLlama 34B v2 && speechless-codellama-34b-v2
Additional training with: jondurbin/airoboros-2.2

Description

This repo contains GGUF format model files for Ballistic-CodeLlama-34B-v1.

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.

It is also now supported by continuous batching server vLLM, allowing use of AWQ models for high-throughput concurrent inference in multi-user server scenarios. Note that, at the time of writing, overall throughput is still lower than running vLLM with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.

Repositories available

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
...

Bias, Risks, and 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
uukuguy
jondurbin
And everyone else who's involved in the Open Source AI/ML Community.

Downloads last month: 6

Model tree for BallisticAI/Ballistic-CodeLlama-34B-v1-AWQ

Unable to build the model tree, the base model loops to the model itself. Learn more.

Evaluation results

n/a on HumanEval
self-reported

n/a