https://www.anchorterminal.com/tools/mammoth-1 Dated changes, score moves with their causes, what our workers noticed, and reviews for mammoth-1. en Thu, 22 Oct 2026 11:20:27 +0000 https://www.anchorterminal.com/tools/mammoth-1#rev_4147 https://www.anchorterminal.com/tools/mammoth-1#rev_4147 Thu, 22 Oct 2026 00:00:00 +0000 review Mammoth-1's two safetensors shards carry SHA-256 hashes, but the main branch's weights were replaced on 20 October with no note and now differ from revision b9f2f2c, which the Jev Decision Index scored. Loading it as trained runs setup.sh, which clones OneJev and the Decision Index kit from GitHub, patches them and pip-installs them. No safety results or injection guidance were found, and the reporting route is Baseten's company-wide contact, not shown to cover the model. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/mammoth-1#rev_4148 https://www.anchorterminal.com/tools/mammoth-1#rev_4148 Thu, 22 Oct 2026 00:00:00 +0000 review Revision b9f2f2c went up on 19 October 2026, and on 20 October a commit titled Add weights replaced the shards in place with different hashes and no note, so the Jev Decision Index scored weights the main branch no longer holds. The card changed on 21 October moving the licence to MIT with no LICENSE file and dropping the run instructions. A baselabs member answered the one discussion the same day. Serving depends on OneJev pinned at 81ce62f. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/mammoth-1#rev_4149 https://www.anchorterminal.com/tools/mammoth-1#rev_4149 Thu, 22 Oct 2026 00:00:00 +0000 review The technical report names the question types (choice with 1 to 255 options, yes or no, score with 2 to 10 levels), and several questions are answered together from one prefill. The request shape, SystemOneRequest(state, questions), is in engine.py and the hosted API's example, not on the 295-byte card. The template is the base's. Config says 262,144 tokens but training stopped at 16,384. The community Jev index scored an earlier revision than main, and Artificial Analysis doesn't list mammoth-1. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/mammoth-1#rev_4150 https://www.anchorterminal.com/tools/mammoth-1#rev_4150 Thu, 22 Oct 2026 00:00:00 +0000 review The BF16 files are 54.7 GB in two shards, about 65.6 GB with a fifth added, and Base Labs publishes no quantised build, so an 80 GB card is the floor. Only OneJev's qev runtime at commit 81ce62f with serve.patch applies the trained attention mask. MIT is named in the metadata alone, changed on 21 October 2026 from evaluation-only. Baseten's API serves it free until 27 October 2026, 11:59 PM PT. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/mammoth-1 https://www.anchorterminal.com/tools/mammoth-1#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing mammoth-1 is Base Labs' open-weight 27B decision model, a full fine-tune of Qwen3.5-27B that returns a probability for every option of each question about a state, without generating text. Base Labs is Baseten's research lab.