pszemraj

from transformers import AutoProcessor, AutoModelForImageTextToText
from transformers.image_utils import load_image

# Load model and processor
model_id = "LiquidAI/LFM2-VL-1.6B"
model = AutoModelForImageTextToText.from_pretrained(
    model_id, device_map="auto", torch_dtype="bfloat16", trust_remote_code=True
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

pszemraj

# Font configuration - all font settings in ONE section
[font]
size = 15.0
builtin_box_drawing = false  # 0xProto has its own box drawing chars

[font.normal]
family = "0xProto"
style = "Regular"

[font.bold]

pszemraj

%%writefile emoji_search.py
#!/usr/bin/env python3
"""
Emoji Semantic Search CLI

reqs:
    pip install fire sentence-transformers pandas numpy
    
Usage:
    python emoji_search.py "that is flames"

pszemraj

LLM Foundry Configuration Reference

This document provides a comprehensive reference for all configuration options available in LLM Foundry YAML files. Configuration files are used for training, fine-tuning, and evaluating large language models.

Table of Contents

• Configuration Format Types
• Variables
• Model Configuration
• MPT Model Options

pszemraj

# -*- coding: utf-8 -*-
"""gemma-3n-test

pip install -U -q git+https://github.com/huggingface/transformers.git
pip install -U -q git+https://github.com/huggingface/pytorch-image-models.git
"""

from transformers import pipeline
import torch

pszemraj

#!/usr/bin/env python3
"""
Slice a (possibly very tall) image into fixed-height chunks.

Creates a sibling directory called  <image stem>_slices/
and writes   slice_000.png, slice_001.png, …  inside it.
"""

import argparse
from pathlib import Path

pszemraj

"""
Create & save an hf dataset with train/test/val splits from dir w/ text files

Ideal structure:

    root / section_name_1 / file 1
    root / section_name_1 / file 2
    root / section_name_1 / file YYY
    root / section_name_2 / file 1
    root / section_name_2 / file ZZZ

pszemraj

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Standalone Asynchronous Nanonets-OCR-s Inference Script using vLLM and PyMuPDF.

This script processes PDF files from an input directory using the
nanonets/Nanonets-OCR-s model served locally by vLLM via its OpenAI-compatible API.
It renders each page, sends API requests concurrently for OCR, extracts the
structured markdown/HTML text, and saves the combined text for each PDF into a
corresponding .txt file in the specified output directory.

pszemraj

from dataclasses import dataclass
from typing import List, Optional, Tuple

import torch
import torch.nn as nn


@dataclass
class _LayerSummary:
    """A dataclass to hold summary information for a single layer."""

pszemraj

"""
WaveNet: An Ultra-Small Language Model (PyTorch Implementation)

Based on the paper: https://arxiv.org/abs/2411.02674
Hugging Face Transformers compatible implementation.
"""
import math
from typing import Dict, Optional, Tuple, Union

import torch