Moirai GGUF

--- license: cc-by-nc-4.0 library_name: gguf pipeline_tag: time-series-forecasting language: - en base_model: Salesforce/moirai-1.0-R-large base_model_relation: quantized quantized_by: amaye15 tags: - gguf - time-series - forecasting - zero-shot - universal-forecasting - rust inference: false --- # Moirai-1.0-R-large (Salesforce) — GGUF > **⚠️ Non-commercial license.** These weights are CC-BY-NC-4.0 — see [License](#license) below before using them in any commercial product or service. GGUF conversion of [Salesforce's Moirai-1.0-R-large](https://huggingface.co/Salesforce/moirai-1.0-R-large) — a universal forecasting foundation model. Converted and run with [**zsfm**](https://github.com/amaye15/zsfm-rs), a Rust workspace that ports zero-shot forecasting and tabular foundation models to GGUF + [candle](https://github.com/huggingface/candle). No PyTorch, no Python runtime required to run inference. | F32 | F16 | Q8_0 | |---|---|---| | `moirai-f32.gguf` | `moirai-f16.gguf` | `moirai-q8.gguf` | F16 is generally the best size/accuracy trade-off; Q8_0 is smallest. This repo's default recommendation matches the upstream conversion default: **F32**. **Context must be at least 32 timesteps** (Moirai pads short contexts up to a full patch rather than rejecting them, but 32 gives a meaningful example) — a shorter context fails with `context too short`. The examples below use a 32-value context. ## Use it ### Python (`pip install zsfm`) ```bash pip install zsfm huggingface_hub ``` ```python import zsfm from huggingface_hub import hf_hub_download gguf_path = hf_hub_download("amaye15/moirai-gguf", "moirai-f32.gguf") model = zsfm.MoiraiModel(gguf_path) context = [0.85, 0.93, 1.01, 1.09, 1.17, 1.25, 1.33, 1.06, 1.14, 1.22, 1.3, 1.38, 1.46, 1.54, 1.27, 1.35, 1.43, 1.51, 1.59, 1.67, 1.75, 1.48, 1.56, 1.64, 1.72, 1.8, 1.88, 1.96, 1.69, 1.77, 1.85, 1.93] point = model.forecast(context, horizon=64) # -> List[float], the point forecast ``` Moirai's Rust port is architecturally point-forecast only (no quantile/distribution decomposition is computed anywhere in this port, on the CLI or Python side) — `forecast()` here is already the full available output, not an abbreviation of a richer CLI result. The CLI (below) additionally supports batched and multivariate requests, still point-only. ### Rust / CLI (`cargo install zsfm`) ```bash cargo install zsfm --loc...

--- license: mit library_name: gguf pipeline_tag: time-series-forecasting language: - en base_model: Salesforce/moirai-1.0-R-large base_model_relation: quantized quantized_by: amaye15 tags: - gguf - time-series - forecasting - zero-shot - transformer - universal-forecasting - rust inference: false --- # moirai-rs Pure Rust converter and inference engine for [Salesforce/moirai-1.0-R-large](https://huggingface.co/Salesforce/moirai-1.0-R-large). Pre-converted GGUF files are available at [amaye15/moirai-gguf](https://huggingface.co/amaye15/moirai-gguf). Produces GGUF v3 files and runs native forecasting — no Python required. ## Build ```bash cargo build --release ``` ## Convert Downloads the model from HuggingFace and writes a GGUF file: ```bash # F16 (recommended) ./target/release/moirai-rs convert --model Salesforce/moirai-1.0-R-large --dtype f16 --output gguf/moirai-f16.gguf # Q8_0 (smallest) ./target/release/moirai-rs convert --dtype q8 --output gguf/moirai-q8.gguf # F32 (full precision) ./target/release/moirai-rs convert --dtype f32 --output gguf/moirai-f32.gguf ``` To convert all dtypes at once: ```bash ./scripts/convert_all.sh ``` HuggingFace token (optional for public models): ```bash HF_TOKEN=hf_... ./scripts/convert_all.sh ``` ## Inspect tensors Print all tensor names and shapes from a `.safetensors` checkpoint: ```bash ./target/release/moirai-rs inspect-tensors models/model.safetensors ``` ## Infer Run forecasting from stdin JSON: ```bash echo '{"context": [1.0, 1.2, 1.5, 1.3, 1.8, 2.0, 1.9, 2.1], "horizon": 96}' \ | ./target/release/moirai-rs infer --gguf gguf/moirai-f16.gguf ``` Output is JSON in an OpenAI-compatible forecast format: ```json { "id": "forecast-000001932b7a1234", "object": "forecast", "created": 1749686400, "model": "moirai", "choices": [{ "index": 0, "forecast": { "point": [2.1, 2.3, 2.5, "..."], "quantiles": {} }, "finish_reason": "stop" }], "usage": {"context_length": 8, "forecast_length": 96} } ``` **Batch inference** — pass multiple series as a nested array to get one `Choice` per series: ```bash echo '{"context": [[1.0, 1.2, 1.5], [2.0, 2.2, 2.5]], "horizon": 96}' \ | ./target/release/moirai-rs infer --gguf gguf/moirai-f16.gguf ``` **Multivariate inference** — pass a 3D context array `[batch][variate][time]` to get a `variates` array in each choice. Each variate is processed ind...

Source context: 82 downloads · 0 likes · Pipeline time-series-forecasting · Library gguf · Repo amaye15/moirai-gguf