Quantization made by Richard Erkhov.

Dracarys2-72B-Instruct - GGUF

Model creator: https://huggingface.co/abacusai/
Original model: https://huggingface.co/abacusai/Dracarys2-72B-Instruct/

Name	Quant method	Size
Dracarys2-72B-Instruct.Q2_K.gguf	Q2_K	27.76GB
Dracarys2-72B-Instruct.IQ3_XS.gguf	IQ3_XS	30.59GB
Dracarys2-72B-Instruct.IQ3_S.gguf	IQ3_S	32.12GB
Dracarys2-72B-Instruct.Q3_K_S.gguf	Q3_K_S	32.12GB
Dracarys2-72B-Instruct.IQ3_M.gguf	IQ3_M	33.07GB
Dracarys2-72B-Instruct.Q3_K.gguf	Q3_K	35.11GB
Dracarys2-72B-Instruct.Q3_K_M.gguf	Q3_K_M	29.28GB
Dracarys2-72B-Instruct.Q3_K_L.gguf	Q3_K_L	36.79GB
Dracarys2-72B-Instruct.IQ4_XS.gguf	IQ4_XS	7.05GB
Dracarys2-72B-Instruct.Q4_0.gguf	Q4_0	38.4GB
Dracarys2-72B-Instruct.IQ4_NL.gguf	IQ4_NL	38.9GB
Dracarys2-72B-Instruct.Q4_K_S.gguf	Q4_K_S	40.88GB
Dracarys2-72B-Instruct.Q4_K.gguf	Q4_K	44.16GB
Dracarys2-72B-Instruct.Q4_K_M.gguf	Q4_K_M	44.16GB
Dracarys2-72B-Instruct.Q4_1.gguf	Q4_1	42.56GB
Dracarys2-72B-Instruct.Q5_0.gguf	Q5_0	46.72GB
Dracarys2-72B-Instruct.Q5_K_S.gguf	Q5_K_S	47.85GB
Dracarys2-72B-Instruct.Q5_K.gguf	Q5_K	50.71GB
Dracarys2-72B-Instruct.Q5_K_M.gguf	Q5_K_M	50.71GB
Dracarys2-72B-Instruct.Q5_1.gguf	Q5_1	34.61GB
Dracarys2-72B-Instruct.Q6_K.gguf	Q6_K	59.93GB
Dracarys2-72B-Instruct.Q8_0.gguf	Q8_0	71.96GB

Original model description:

language: - en license: other tags: - chat license_name: tongyi-qianwen license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE pipeline_tag: text-generation

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