Marcial Igme igmeMarcial

🎯

Focusing

software engineer

igmeMarcial / hf_mcp.py

Created May 7, 2025 23:13 — forked from Wauplin/hf_mcp.py

Python-based HF MCP server

	"""
	WARNING: This is an experimental implementation. Expect rough edges while using it.

	-------------------------------------------------
	Defines a FastMCP server that exposes the Hugging Face Hub API as a set of tools.

	In practice, all public methods from `HfApi` are exposed as tools, except for the ones dealing with files:
	- `create_commit`
	- `hf_hub_download`
	- `preupload_lfs_files`

igmeMarcial / youtube.py

Created April 16, 2025 21:06 — forked from philschmid/youtube.py

	import os
	from google import genai
	from google.genai import types

	client = genai.Client(api_key=os.getenv("GEMINI_API_KEY","xxx"))

	# Repalce with the youtube url you want to analyze
	youtube_url = "https://www.youtube.com/watch?v=RDOMKIw1aF4"

	# Prompt to analyze and summarize the Youtube Video

igmeMarcial / get_memory_size.py

Last active May 7, 2025 23:17 — forked from philschmid/get_memory_size.py

Get needed GPU per precision for a Hugging Face Model Id

	from typing import Dict, Union
	from huggingface_hub import get_safetensors_metadata
	import argparse
	import sys

	# Example:
	# python get_gpu_memory.py Qwen/Qwen2.5-7B-Instruct

	# Dictionary mapping dtype strings to their byte sizes
	bytes_per_dtype: Dict[str, float] = {

igmeMarcial / grpo_demo.py

Created February 1, 2025 00:43 — forked from willccbb/grpo_demo.py

GRPO Llama-1B

	# train_grpo.py
	import re
	import torch
	from datasets import load_dataset, Dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import LoraConfig
	from trl import GRPOConfig, GRPOTrainer

	# Load and prep dataset