Gliese-CUA-Tool-Call-8B-FP8

Gliese-CUA-Tool-Call-8B-FP8 is an FP8-compressed variant built on top of prithivMLmods/Gliese-CUA-Tool-Call-8B. This edition applies BF16 · FP8 (F8_E4M3) precision formats to significantly reduce memory footprint and improve inference throughput while preserving the structured tool-calling and multimodal agent capabilities of the original 8B architecture. The base Gliese-CUA-Tool-Call-8B model is a Computer Use Agent (CUA) multimodal system derived from Qwen2.5-VL-7B-Instruct. It is designed for GUI understanding, UI localization, and action execution across web, desktop, and mobile environments. The model emphasizes visual grounding, intent-driven action generation, and UI-based question answering, enabling reliable interaction with real-world software interfaces. It is optimized for agentic tool calling, producing structured outputs that can be directly executed by downstream systems.

FP8 (8-bit floating point) weight and activation quantization using hardware acceleration on GPUs – FP8 W8A8. Quantization W8A8 FP8-dynamic recipe – examples.

Key Highlights

• BF16 · FP8 (F8_E4M3) Compression: Transformer Engine based FP8 quantization reduces VRAM usage and improves inference efficiency while maintaining structured action accuracy.
• Computer Use Agent Architecture: Designed for multimodal GUI reasoning and environment interaction.
• Agentic Tool Calling: Generates structured, machine-executable tool calls suitable for automation pipelines.
• Visual Grounding: Accurately interprets UI elements, layout hierarchies, and on-screen context.
• Intent-Driven Actioning: Converts natural language instructions into executable UI actions.
• Cross-Platform Support: Applicable across web apps, desktop software, and mobile interfaces.
• Optimized Deployment: FP8 compression enables more efficient deployment on compatible GPU architectures with reduced memory overhead.

Quick Start with Transformers

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch

# Load the FP8 CUA Tool Call model
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Gliese-CUA-Tool-Call-8B-FP8",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Gliese-CUA-Tool-Call-8B-FP8"
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "screenshot.png",
            },
            {"type": "text", "text": "Click the settings icon and open the preferences menu."},
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

image_inputs, video_inputs = process_vision_info(messages)

inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
).to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=256)

generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]

output_text = processor.batch_decode(
    generated_ids_trimmed,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False
)

print(output_text)

Intended Use

• GUI Automation Research: Studying multimodal grounding in software environments.
• Agentic Systems Development: Building structured tool-calling pipelines.
• UI-Based Question Answering: Extracting information from complex interface layouts.
• Web and Desktop Automation: Executing structured action sequences in live applications.
• Human-Computer Interaction Research: Evaluating intent-to-action alignment in multimodal agents.

Limitations & Risks

Important: This model generates executable structured actions.

• Execution Risk: Generated tool calls may trigger real actions if connected to live systems. Proper validation layers are strongly recommended.
• Context Sensitivity: Performance depends heavily on screenshot clarity and UI complexity.
• Hardware Requirements: FP8 requires compatible GPU hardware support for optimal performance.