Hoags-2B-Exp

[!WARNING] Note: This model contains artifacts and may perform poorly in some cases.

Hoags-2B-Exp

The Hoags-2B-Exp model is a fine-tuned version of Qwen2-VL-2B-Instruct, specifically designed for reasoning tasks, context reasoning, and multi-modal understanding. If you ask for an image description, it will automatically describe the image and answer the question in a conversational manner.

Key Enhancements

• Advanced Contextual Reasoning: Hoags-2B-Exp achieves state-of-the-art performance in reasoning tasks by enhancing logical inference and decision-making.

• Understanding images of various resolution & ratio: The model excels at visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.

• Long-Context Video Understanding: Capable of processing and reasoning over videos of 20 minutes or more for high-quality video-based question answering, content creation, and dialogue.

• Device Integration: With strong reasoning and decision-making abilities, the model can be integrated into mobile devices, robots, and automation systems for real-time operation based on both visual and textual input.

• Multilingual Support: Supports text understanding in various languages within images, including English, Chinese, Japanese, Korean, Arabic, most European languages, and Vietnamese.

Demo Inference

How to Use

instruction = "Analyze the image and generate a clear, concise description of the scene, objects, and actions. Respond to user queries with accurate, relevant details derived from the visual content. Maintain a natural conversational flow and ensure logical consistency. Summarize or clarify as needed for understanding."

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

# Load the model with automatic device placement
model = Qwen2VLForConditionalGeneration.from_pretrained(
    "prithivMLmods/Hoags-2B-Exp", torch_dtype="auto", device_map="auto"
)

# Recommended: Enable flash_attention_2 for better performance in multi-image and video tasks
# model = Qwen2VLForConditionalGeneration.from_pretrained(
#     "prithivMLmods/Hoags-2B-Exp",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
#     device_map="auto",
# )

# Load processor
processor = AutoProcessor.from_pretrained("prithivMLmods/Hoags-2B-Exp")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
            },
            {"type": "text", "text": "Analyze the context of this image."},
        ],
    }
]

# Prepare input
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",
)
inputs = inputs.to("cuda")

# Inference
generated_ids = model.generate(**inputs, max_new_tokens=128)
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)

Buffer Handling

buffer = ""
for new_text in streamer:
    buffer += new_text
    buffer = buffer.replace("<|im_end|>", "")
    yield buffer

Key Features

1. Advanced Contextual Reasoning:

   • Optimized for context-aware problem-solving and logical inference.

2. Optical Character Recognition (OCR):

   • Extracts and processes text from images with exceptional accuracy.

3. Mathematical and Logical Problem Solving:

   • Supports complex reasoning and outputs equations in LaTeX format.

4. Conversational and Multi-Turn Interaction:

   • Handles multi-turn dialogue with enhanced memory retention and response coherence.

5. Multi-Modal Inputs & Outputs:

   • Processes images, text, and combined inputs to generate insightful analyses.

6. Secure and Efficient Model Loading:

   • Uses Safetensors for faster and more secure model weight handling.