laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888

🤗 Hugging Face 来源text-generationapache-2.067.1B 参数激活 2B134 GBsafetensors✓ 40 个校验和今天更新

一条命令提交

在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对，然后提交。你只需开始做种，并粘贴你账户中的密钥。它只读取你的文件，绝不修改。如果愿意，可以先阅读脚本。

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo laion/snowball-67b-a2b-sft-s3-nemotron-terminal-step1888 ./model-folder

需要做种者 →

Snowball 67B-A2B Nemotron-Terminal SFT

This repository contains BF16 Hugging Face/vLLM exports from the Nemotron-Terminal branch of Marin's ordered Chat → Thinking → Agentic SFT campaign. The model was initialized from the final Thinking checkpoint and trained for 1,888 steps on the Nemotron Terminal corpus used by the successful control in marin-community/marin#7743.

main is the final step-1,888 checkpoint. Retained intermediate checkpoints are published as step-N branches.

Provenance

Native checkpoint collection:

s3://marin-us-east-02a/marin/grug/snowball_step105149_sft_s3_nemotron_terminal_steps1888/2026.08.14.1/checkpoints/

The export preserves the Marin tokenizer, Delphi special tokens, and the trained FP32 query-bias state. This lineage should be evaluated with Terminus-2.