Downloads, merges LoRA adapters, and publishes models to HuggingFace Hub.
npx skills add https://github.com/thinking-machines-lab/tinker-cookbook --skill weights
Please help me install this Agent Skill. Skill: weights Source: https://github.com/thinking-machines-lab/tinker-cookbook/tree/main/.claude/skills/weights Command: npx skills add https://github.com/thinking-machines-lab/tinker-cookbook --skill weights
Fine-tuned model workflows often require moving weights between systems, merging adapters, and publishing finished models. This Skill standardizes and automates those steps to reduce manual overhead and errors.
Download a LoRA adapter, merge it into a base model, and publish the final model to HuggingFace.
High-intent search queries and answers about installing and using this skill.
To merge LoRA adapters into a base model, the weights Skill uses the build_hf_model function. It takes adapter_path inputs and a base_model selection to combine them into a deployable HuggingFace artifact.
Downloading trained adapters from Tinker is handled by the weights Skill's download function. It automates retrieving the trained LoRA adapter files from Tinker and stores them locally for subsequent processing.
Yes, you can publish a merged model to HuggingFace Hub using the publish_to_hf_hub function. It supports uploading finished artifacts directly to HFHub, including options for private repository publishing.
Automating the fine-tuned model weight lifecycle is streamlined by standardizing adapter downloads, LoRA merging, and HuggingFace publishing. This reduces manual overhead and errors when moving weights between systems for deployment.
Yes, the weight lifecycle workflow supports dtype options during the merging process. When using build_hf_model to merge LoRA adapters into the base model, you can specify the desired data type for the output artifact.
thinking-machines-labAutomate Tinker training runs and checkpoint management via CLI, including HuggingFace Hub publishing.
jayll1303Deploy HuggingFace TEI Docker images for embedding and re-ranking inference.
North-Shore-AIDeploy Chiral Narrative Synthesis with a Tinker-based training and evaluation pipeline.
Axel-DaMageConfigure LoRA/QLoRA adapters and hyperparameters for fine-tuning large language models.
