sugatoray

import os
import torch
import psutil
import datasets
import glob

from transformers import (
    AutoTokenizer, LlamaConfig, LlamaForCausalLM, Trainer, TrainingArguments,
    DataCollatorForLanguageModeling
)

sugatoray

# /// script
# requires-python = ">=3.11,<3.12"
# dependencies = [
#     "distilabel[mlx]",
# ]
# ///
from distilabel.models import MlxLLM
from distilabel.pipeline import InstructionResponsePipeline

llm = MlxLLM(

sugatoray

# /// script
# requires-python = ">=3.11,<3.12"
# dependencies = [
#     "distilabel[hf-transformers, hf-inference-endpoints]",
# ]
# ///
from distilabel.models import InferenceEndpointsLLM
from distilabel.pipeline import InstructionResponsePipeline

repo_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"

sugatoray

HF Model License Top20 Dist

• source: HF Model Metadata
• author: Sugato Ray @sugatoray

sugatoray

# requires sentence_transformers>=3.2.0
from sentence_transformers import SentenceTransformer, export_optimized_onnx_model, export_dynamic_quantized_onnx_model

# The model to export to ONNX (+ optimize, quantize), OpenVINO
model_id = "mixedbread-ai/mxbai-embed-large-v1"
# Where to save the exported models locally
output_dir = model_id.replace("/", "-")

onnx_model = SentenceTransformer(model_id, backend="onnx", model_kwargs={"export": True})
onnx_model.save_pretrained(output_dir)

sugatoray

Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches.
Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed.
Use <count> tags after each step to show the remaining budget. Stop when reaching 0.
Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress.
Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process.
Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach:

0.8+: Continue current approach
0.5-0.7: Consider minor adjustments
Below 0.5: Seriously consider backtracking and trying a different approach

sugatoray

#VERBOSE=0 torchrun --nproc_per_node 3 self_contained_pp_LOC.py
import os, random, numpy as np, torch, torch.nn as nn, torch.distributed as dist, torch.nn.functional as F
from torch.optim import AdamW
from torch.utils.data import DataLoader, DistributedSampler
from datasets import load_dataset
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer

STEP, local_rank, world_size, verbose = 0, int(os.environ["LOCAL_RANK"]), int(os.environ["WORLD_SIZE"]), os.environ.get("VERBOSE", "0") == "1"

def set_all_seed(seed):

sugatoray

"""
A minimal, fast example generating text with Llama 3.1 in MLX.

To run, install the requirements:

    pip install -U mlx transformers fire

Then generate text with:

    python l3min.py "How tall is K2?"

sugatoray

MLX LM with the OpenAI Python Package

1. Install

Install MLX LM and openai:

pip install mlx-lm openai

sugatoray

MLX LM with the OpenAI Python Package

1. Install

Install MLX LM and openai:

pip install mlx-lm openai