download_model
Download a Hugging Face model via the hf CLI for llama.cpp/TabbyAPI/vLLM servers when pull_model doesn't apply; runs as a background job, so poll with get_job.
Instructions
Download a model from Hugging Face via the hf CLI (for llama.cpp/TabbyAPI/vLLM-style servers where pull_model doesn't apply). Runs as a background job — poll with get_job. e.g. repo 'bartowski/Qwen2.5-Coder-7B-Instruct-GGUF' with include 'Q4_K_M'.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"repo": "<repo>"
},
"name": "download_model"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| repo | Yes | HF repo id, e.g. 'bartowski/Qwen2.5-Coder-7B-Instruct-GGUF' | |
| include | No | Filename glob filter, e.g. '*Q4_K_M*.gguf' | |
| revision | No | Branch/tag/commit (default: main) | |
| local_dir | No | Destination dir (must be inside allowed roots; default: HF cache) |