mzbac’s gists

mzbac / gist:e0526c49f4279f9bd06305cf7480be11

Last active August 18, 2025 07:42

mfe demo

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>Micro Frontend Demo</title>
	<style>
	body {
	font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
	margin: 0;

mzbac / gist:754829a569f57232d2bcac3eb91a44df

Created July 26, 2025 13:14

automator grammar check

	function escapeShellArg(str) {
	return "'" + str.replace(/'/g, "'\\''") + "'";
	}

	const removeBackticks = (str) => {
	// remove leading backticks
	str = str.replace(/^(```\n\|```)/g, "");

	// remove tailing backticks and everything after
	const index = str.lastIndexOf("```");

mzbac / Qwen3 embedding

Last active October 22, 2025 05:47

Qwen3 embedding

	import mlx.core as mx
	import mlx.nn as nn
	from typing import Tuple, Type, Optional, List, Any
	import importlib
	from transformers import AutoTokenizer
	from mlx_lm.utils import load_model, get_model_path


	def get_qwen3_embedding_classes(config: dict) -> Tuple[Type[nn.Module], Type]:

mzbac / gist:866a3c7c9b927177a124256720acbc63

Created May 25, 2025 15:18

ScreenMate Implementation Documentation

	# Implementation Documentation for Agentic LLM Workflow: macOS ScreenMate (SwiftUI First - Direct VLM, In-Memory Screenshot, Custom Prompts)

	## 1. Overall Project Goal:
	Develop a native macOS application ("ScreenMate") that:
	* Runs as a menubar accessory application (no Dock icon).
	* Provides advanced image understanding functionality triggered by a screenshot, capturing the image into memory (as an `NSImage`) and processing it using a locally loaded Vision Language Model (VLM) via MLX Swift, with an option for users to provide custom prompts. (OCR is one of its capabilities).
	* Features a main interface in a menubar popover panel.
	* Features a "Custom Prompt" floating panel allowing users to input their own VLM prompts for image processing.
	* Allows configuration for auto-starting at login and selecting a VLM model from a predefined list.
	* Uses SwiftUI for UI components where feasible, and AppKit for system integrations and panel management.

mzbac / gist:96d8427542496fd75ca67849b5cb6ce9

Created May 7, 2025 14:28

Use MLX-LM for text embeddings

	import mlx.core as mx
	import numpy as np
	from transformers import PreTrainedTokenizer, AutoModel, AutoTokenizer
	import torch
	import torch.nn.functional as F
	from torch import Tensor
	from typing import List, Dict, Any, Tuple
	from mlx_lm.utils import load

	def tokenize_texts(

mzbac / gist:06c932b0884771fa59e786b348ddbb5e

Created May 7, 2025 08:23

MLX LLM embedding

	import mlx.core as mx
	import numpy as np
	from transformers import PreTrainedTokenizer, AutoModel, AutoTokenizer
	import torch
	import torch.nn.functional as F
	from torch import Tensor
	from typing import List, Dict, Any
	from mlx_lm.utils import load

	def tokenize_texts(

mzbac / cohere-v3-english-embedding.json

Created May 1, 2025 11:55 — forked from didier-durand/cohere-v3-english-embedding.json

Embedding request / reponse by Cohere v3 English on user prompt "What is django?"

	{
	"schemaType": "ModelInvocationLog",
	"schemaVersion": "1.0",
	"timestamp": "2024-05-30T06:22:26Z",
	"accountId": "<account-id>",
	"identity": {
	"arn": "<identity-arn>"
	},
	"region": "us-west-2",
	"requestId": "de4843a4-8b97-46a9-b005-878dfdf0a123",

mzbac / gist:0f846e762ede4cb1b2372dc24ae4b264

Last active July 26, 2024 01:40

mxl-sharding

	install `pip install mlx-sharding`

	For shard node:
	Run `mlx-sharding-server --model mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx --start-layer 14 --end-layer 27`

	For primary node:
	Run `mlx-sharding-api --model mlx-community/DeepSeek-Coder-V2-Lite-Instruct-4bit-mlx --start-layer 0 --end-layer 14 --llm-shard-addresses <your shard node address>`

mzbac / gist:9846a963ea28723bd8d769049cf213be

Created April 28, 2024 01:25

tool use

	def extract_arguments(json_str):
	json_str = json_str.replace("'", '"')
	start_index = json_str.find('"arguments":') + len('"arguments":')

	start_of_json = json_str.find("{", start_index)
	end_of_json = json_str.rfind("}")

	if start_of_json != -1 and end_of_json != -1:
	extracted = json_str[start_of_json:end_of_json]
	if (extracted.startswith("'") and extracted.endswith("'")) or (

mzbac / gist:c10ba6b8cad89942c8924a27e82a1455

Created April 27, 2024 06:51

preprocess.py

	from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments,BitsAndBytesConfig
	from datasets import load_dataset

	model_name ="meta-llama/Meta-Llama-3-8B-Instruct"
	tokenizer = AutoTokenizer.from_pretrained(model_name)

	dataset = load_dataset("glaiveai/glaive-function-calling-v2",split="train")

	def formatting_prompts_func(example):
	output_texts = []

Anchen mzbac