Reply to thread

Message: <blockquote data-quote="MihiCherub" data-source="post: 30386119" data-attributes="member: 238676">Meta introduces Llama 3.3, a 70B parameter model delivering performance comparable to Llama 3.1 405B but with significantly lower computational demands.<img src="https://media.datacamp.com/cms/ad_4nxceo65lqgskpt2gyjdxnyxikzmv_t-3njxvxaqiklpa-hbtvmpmipofzejtrxzdfs2byf_abs10_hfrknvkxzlzxlr0fvtgipmzktuwxhok7awlmun10ox6ahwyou_2r_gyatf4.png" alt="" class="fr-fic fr-dii fr-draggable " style="width: 501px" />Meta AI has just introduced Llama 3.3, a 70-billion parameter model that delivers performance comparable to the much larger <a href="https://www.datacamp.com/blog/llama-3-1-405b-meta-ai" target="_blank">Llama 3.1 405B</a>, but with far lower computational demands.<a href="https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct" target="_blank">https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct</a>    <table style='width: 100%'><tr><th> </th><th>Training Data </th><th>Params </th><th>Input modalities </th><th>Output modalities </th><th>Context length </th><th>GQA </th><th>Token count </th><th>Knowledge cutoff </th></tr><tr><td>Llama 3.3 (text only) </td><td>A new mix of publicly available online data. </td><td>70B </td><td>Multilingual Text </td><td>Multilingual Text and code </td><td>128k </td><td>Yes </td><td>15T+ </td><td>December 2023 </td></tr></table>Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai.Llama 3.3 model. Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.Model Release Date:<ul> <li data-xf-list-type="ul">70B Instruct: December 6, 2024</li> </ul><img src="https://media.datacamp.com/cms/ad_4nxcgxjt1c5ju_yrd5tu6o7voalwjren2u-us_snst8csi-iljoa577shvw9egrhkbokjxsxnwhoe_jp-ug4sjpg2n0v7ot7osoejzjq3hiqs9l4yamazydozbsokt1_kt8s2bdiy1w.png" alt="" class="fr-fic fr-dii fr-draggable " style="width: 820px" /></blockquote>

Verification: Asuwa dahayen wadi kalama keeyada?

Top Bottom