Instructions to use abacusai/Dracarys2-72B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abacusai/Dracarys2-72B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="abacusai/Dracarys2-72B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abacusai/Dracarys2-72B-Instruct")
model = AutoModelForCausalLM.from_pretrained("abacusai/Dracarys2-72B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abacusai/Dracarys2-72B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abacusai/Dracarys2-72B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/Dracarys2-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abacusai/Dracarys2-72B-Instruct

SGLang

How to use abacusai/Dracarys2-72B-Instruct 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 "abacusai/Dracarys2-72B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/Dracarys2-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "abacusai/Dracarys2-72B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abacusai/Dracarys2-72B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abacusai/Dracarys2-72B-Instruct with Docker Model Runner:
```
docker model run hf.co/abacusai/Dracarys2-72B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Dracarys2-72B-Instruct

Introduction

We introduce the latest in the Smaug series, the Dracarys family of finetunes targeting coding performance improvements across a variety of base models.

This variant is a finetune of Qwen2.5-72B-Instruct

Compared to Qwen2.5-72B-Instruct, Dracarys has better LiveCodeBench scores (see evaluation results below).

Model Description

Developed by: Abacus.AI
License: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
Finetuned from model: Qwen2.5-72B-Instruct.

How to use

The prompt format is unchanged from Qwen2.5-72B-Instruct (see evaluations for prompt details for LCB)

Use with transformers

See the snippet below for usage with Transformers:

import transformers
import torch

model_id = "abacusai/Dracarys2-72B-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are data science coding assistant that generates Python code using Pandas and Numpy."},
    {"role": "user", "content": "Write code to select rows from the dataframe `df` having the maximum `temp` for each `city`"},
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])

Evaluation Results

LiveCodeBench

Model	Code Generation	Code Execution (COT)	Test Output Prediction
Dracarys2-72B-Instruct	53.80	89.12	59.61
Qwen2.5-72B-Instruct	53.03	88.72	46.28

Breakdown of LiveCodeBench CodeGeneration

Model	Easy	Medium	Hard
Dracarys2-72B-Instruct	88.79	50.28	9.47
Qwen2.5-72B-Instruct	86.99	49.59	9.99

Breakdown of LiveCodeBench TestOutputPrediction

Model	Easy	Medium	Hard
Dracarys2-72B-Instruct	79.25	53.76	37.63
Qwen2.5-72B-Instruct	68.43	39.46	22.22

Downloads last month: 19

Safetensors

Model size

73B params

Tensor type

BF16

Model tree for abacusai/Dracarys2-72B-Instruct

Finetunes

1 model

Merges

5 models

Quantizations

7 models