Crypto Flexs
  • DIRECTORY
  • CRYPTO
    • ETHEREUM
    • BITCOIN
    • ALTCOIN
  • BLOCKCHAIN
  • EXCHANGE
  • TRADING
  • SUBMIT
Crypto Flexs
  • DIRECTORY
  • CRYPTO
    • ETHEREUM
    • BITCOIN
    • ALTCOIN
  • BLOCKCHAIN
  • EXCHANGE
  • TRADING
  • SUBMIT
Crypto Flexs
Home»ADOPTION NEWS»AMD Launches AMD-135M: Innovation in Small Language Models
ADOPTION NEWS

AMD Launches AMD-135M: Innovation in Small Language Models

By Crypto FlexsSeptember 28, 20242 Mins Read
Facebook Twitter Pinterest LinkedIn Tumblr Email
AMD Launches AMD-135M: Innovation in Small Language Models
Share
Facebook Twitter LinkedIn Pinterest Email

Louisa Crawford
September 28, 2024 07:13

AMD unveiled the AMD-135M, the first compact language model with speculative decoding to improve AI model efficiency and performance.





In a significant advancement in artificial intelligence, AMD announced the release of AMD-135M, its first small language model (SLM). According to AMD.com, this new model aims to address some of the limitations faced by large language models (LLMs) such as GPT-4 and Llama while providing specialized functionality.

AMD-135M: The first AMD small language model

Part of the Llama family, the AMD-135M is AMD’s pioneering effort in SLM. The model was trained from scratch using the AMD Instinct™ MI250 accelerator and 670 billion tokens. The training process resulted in two different models: AMD-Llama-135M and AMD-Llama-135M-code. The former was pre-trained with regular data, while the latter was fine-tuned with an additional 20 billion tokens specifically for code data.

prior training: AMD-Llama-135M was trained for 6 days using 4 MI250 nodes. The AMD-Llama-135M code, a code-centric variant, required an additional four days for fine-tuning.

All associated training code, datasets, and model weights are open source, allowing developers to reproduce the model and contribute to the training of other SLMs and LLMs.

Optimization through speculative decoding

One notable advancement in AMD-135M is the use of speculative decoding. Existing autoregressive approaches for large-scale language models often have low memory access efficiency because each forward pass produces only a single token. Speculative decoding solves this problem by using a small draft model to generate candidate tokens and then verifying them with a larger target model. This method allows generating multiple tokens per forward pass, significantly improving memory access efficiency and inference speed.

Accelerate inference performance

AMD tested the performance of the AMD-Llama-135M code with a draft model of CodeLlama-7b on a variety of hardware configurations, including MI250 accelerators and Ryzen™ AI processors. The results show that inference performance is significantly improved when using speculative decoding. This enhancement establishes an end-to-end workflow for training and inference on selected AMD platforms.

next steps

AMD aims to foster innovation within the AI ​​community by providing open source reference implementations. The company encourages developers to explore and contribute to new areas of AI technology.

For more information about the AMD-135M, visit the full technology blog on AMD.com.

Image source: Shutterstock


Share. Facebook Twitter Pinterest LinkedIn Tumblr Email

Related Posts

TRX Price Prediction: TRON targets $0.35-$0.62 despite the current oversold situation.

October 26, 2025

BTC RSI hits April low as Coinbase premium turns red.

October 18, 2025

Crypto Exchange Rollish is expanded to 20 by NY approved.

October 2, 2025
Add A Comment

Comments are closed.

Recent Posts

Pioneering Data Sovereignty Through Real-World Utility And Cultural Heritage

October 31, 2025

$BALZ Brings The Meme Migration Home

October 31, 2025

By The End Of 2025, Everyone Should Know The Best Way To Increase Wealth.

October 31, 2025

Aster’s Rocket Launch Surpasses $1B In Trading Volume, As Nubila Joins With Over 6 Million $NB In Rewards

October 31, 2025

SBF’s

October 31, 2025

Open Miner Cloud Mining Revolutionizes Cryptocurrency Mining, Generating Up To $32,000 In Daily Profits.

October 31, 2025

Analysts predict a 1,500% rally when PEPE price reaches $0.00012.

October 30, 2025

Unibase (UB), Humanity (H), And ConstructKoin (CTK) Are This Week’s Crypto Winners As Decentralized Infra Shines

October 30, 2025

Let AI Work For You — Empowering Everyone To Profit From The Intelligence Era

October 30, 2025

NOWPayments Launches $0 USDT (TRC20) Network Fee Offer For New Partners

October 30, 2025

Jiuzi Holdings Launches $1 Billion Bitcoin Treasury With SOLV To Drive Institutional Yields And RWA Innovation

October 30, 2025

Crypto Flexs is a Professional Cryptocurrency News Platform. Here we will provide you only interesting content, which you will like very much. We’re dedicated to providing you the best of Cryptocurrency. We hope you enjoy our Cryptocurrency News as much as we enjoy offering them to you.

Contact Us : Partner(@)Cryptoflexs.com

Top Insights

Pioneering Data Sovereignty Through Real-World Utility And Cultural Heritage

October 31, 2025

$BALZ Brings The Meme Migration Home

October 31, 2025

By The End Of 2025, Everyone Should Know The Best Way To Increase Wealth.

October 31, 2025
Most Popular

Anthropic Releases Claude 3.5 Sonnet Android App with Advanced AI Features

July 16, 2024

NFT Creator – Cointelegraph Magazine

November 30, 2023

Ethereum price plummets to $2,000 as key support line breaks

January 24, 2024
  • Home
  • About Us
  • Contact Us
  • Disclaimer
  • Privacy Policy
  • Terms and Conditions
© 2025 Crypto Flexs

Type above and press Enter to search. Press Esc to cancel.