Known limitations
What Ertas cannot do today, what is on the roadmap, and the workaround the docs recommend in the meantime.
Ertas is opinionated about what it ships. A small surface area that works well beats a large surface area that has rough edges, especially for a product whose output your users depend on. This page collects everything that the rest of the docs reference as "coming soon" into one place, with the workaround that lets you ship today and a sketch of what to expect when each item lands.
Items here are organised by where they affect you, not by team or priority. If a row says "Coming," it is genuinely on the roadmap. If a row says "Open question," it is being considered but not committed. If a row says "Not planned," it is not on the near horizon.
Models and architectures
Mixture-of-experts (MoE) bases
Status: Not yet supported.
Mixtral, DeepSeek-V2 / V3, Qwen MoE, and other MoE architectures are not yet trainable in Ertas. The dense-transformer catalogue covers everything the platform supports today. MoE adds routing-parameter handling and a much larger VRAM footprint at training time (Mixtral 8x7B has 47B total parameters), so the rollout involves both trainer changes and plan changes.
Workaround: Pick a dense model from the catalogue. Most use cases that point at Mixtral are well served by Mistral 7B Instruct or Qwen 2.5 7B Instruct.
When it ships: File sizes and formats carries a Callout flagging the projected Q4_K_M size for Mixtral 8x7B (~25 to 30 GB). The changelog will tag the addition with Catalogue when it lands.
Vision-language models (VLMs)
Status: Not yet supported.
Llava, Qwen 2.5 VL, and similar multimodal bases are not in the catalogue. Ertas's training pipeline is text-only.
Workaround: For image-to-text use cases, use a separate OCR step (Vision Framework on iOS, ML Kit on Android) and feed the OCR output to a text-only fine-tune. The Structured data extraction recipe demonstrates this pattern.
Quantisation and export
Quantisation levels beyond Q4_K_M
Status: Coming.
Q4_K_M is the only export quantisation today. The roadmap items:
| Level | What it gets you | Expected GGUF size vs Q4_K_M |
|---|---|---|
| Q5_K_M | Slightly higher fidelity | ~25% larger |
| Q8_0 | Near-fp16 quality | ~2x size of Q4 |
| Q3_K_M | Smaller for low-end devices | ~25% smaller |
| Q2_K | Smallest possible | ~40% smaller, measurable quality drop |
Workaround: Local re-quantisation using llama-quantize. The Quantization page walks through the steps; the inputs are the LoRA + merge-with-base + your chosen quantisation level.
ONNX export
Status: Open question.
The transformers.js browser path, ONNX Runtime Mobile, Apple Core ML conversion, and server-side ONNX Runtime deployments all want an ONNX export. The roadmap question is whether to make this a first-class export choice in Ertas or to leave it as a post-training conversion path users run locally.
Workaround: Conversion from a LoRA-merged checkpoint to ONNX via Hugging Face Optimum is well-trodden; the path is outside Ertas today.
Content hash on published GGUFs
Status: Coming.
Ertas does not publish a content hash (SHA-256 or equivalent) alongside the GGUF download today. Integrity verification on first download, change tracking between fine-tune iterations, and supply-chain audit all benefit from one.
Workaround: Compute the SHA-256 yourself on first download and ship the expected hash inside your app's binary. The Verifying exports page and the Ship: model delivery page both document this pattern.
Training and dataset tooling
DPO training
Status: Coming.
Ertas's Fine-Tune Action Module trains with SFT. DPO (Direct Preference Optimisation) is the natural follow-up that lets you train on (prompt, chosen, rejected) preference triples to push past SFT's quality ceiling. See SFT vs DPO.
Workaround: Strong SFT covers most use cases. For the structured-output use case where DPO would help most, the Structured data extraction recipe describes the dataset shape DPO will eventually consume.
Evaluation suite
Status: Coming.
In-app eval that runs a probe set against a trained model and produces a graded table is not yet built. Held-out split detection (auto-attaching an HF dataset's validation split as eval), mid-training eval passes, LLM-judge integration, and common benchmark runners (MMLU, HumanEval, MT-Bench) are all on the roadmap.
Workaround: Post-export probe sets. Every recipe in the Cookbook ships with one. The Verifying exports page walks through the local-runtime version of this.
Dataset export from Data Craft
Status: Coming.
Once a dataset is uploaded into Data Craft, there is no one-click export back to JSONL. Edits made inside Ertas cannot leave Ertas in dataset form today.
Workaround: Keep your original upload as the source of truth, version-controlled outside Ertas. Treat Data Craft edits as transient until export ships.
Dataset cleaning view
Status: Coming.
Bulk detection and fix of common dataset quality issues (formatting drift, accidental refusals, missing fields, length outliers, near-duplicates) is not built. Cleaning today is one row at a time in the Data Craft workspace.
Workaround: Pre-clean datasets in a tool you control before upload (Python + pandas, a spreadsheet, your editor of choice). Ertas's preview helps spot issues; the fix lives upstream.
Run config diff view
Status: Coming.
Comparing two completed runs side by side (LR, batch size, dataset, final loss, runtime) is not built. The Run panel shows each run's config individually.
Workaround: Screenshot or copy the configs into your notes. Most teams pin a "configs" doc per project with the comparisons they care about.
Log download
Status: Not planned.
There is no "Download logs" button on the Run panel. Errors are surfaced inline; the support path for deeper diagnosis is to send the run ID and have an Ertas agent pull server-side logs.
Workaround: Inline errors in the Run panel are usually sufficient. For deeper issues, the support flow in the FAQ.
Dataset attestation audit surface
Status: Coming.
The Hugging Face dataset import requires a rights-attestation checkbox and persists the attestation in metadata, but there is no user-facing audit view to review past attestations. Per-dataset attestation history and account-level CSV export are on the roadmap.
Workaround: Keep a local record of imports. The Import from Hugging Face page flags this in its current state.
Studio surface
CLI
Status: Coming.
There is no Ertas CLI today. The CLI page sketches what is planned: auth, datasets, recipes, runs, artifacts, sweeps.
Workaround: The canvas covers every action a CLI will expose. For sweeps, drop multiple Action Modules on the canvas and run them in parallel.
API and webhooks
Status: Coming.
There is no public API today, so CI integration ("merge a recipe PR, trigger a fine-tune") is not possible. Webhooks for run lifecycle events (started, completed, failed) are part of the same roadmap item.
Workaround: Human-in-the-loop. Designated reviewers open the project and press play.
Multi-account real-time collaboration
Status: Coming.
Multiple accounts editing the same canvas with presence indicators is not built. Teams collaborate today by sharing a single account or by passing the project to a colleague between sessions.
Workaround: Sticky notes on the canvas help with shared context across sessions. See Managing projects.
Team roles (Business plan)
Status: Coming.
Owner / Editor / Viewer roles scoped per project are part of the Business plan roadmap.
Workaround: Until roles ship, project access is all-or-nothing per teammate. For sensitive projects, isolate them in their own account.
Billing caps
Status: Coming.
Monthly soft caps (notify above a threshold) and hard caps (refuse new runs above the threshold; active runs are never killed mid-flight) are not built.
Workaround: Watch the live credit accrual in the Run panel. For long sweeps, run a small calibration first and multiply.
Search within dataset preview, random shuffle
Status: Coming.
The Data Craft dataset preview lists rows in order without a search field or shuffle. Auditing beyond the first N rows requires a download.
Workaround: Audit your dataset before upload; the in-app preview is for spot checks.
Docs catch-up items
A small list of edits that are pending in the docs themselves, not in the product:
concepts.mdxmentions Mixtral in the family rundown without flagging it as not-yet-supported. A small surgical edit is pending.- Some Cookbook recipes assume the in-app eval suite exists. They link to Evaluating a model which currently documents the workarounds rather than the suite. The recipes will be updated when the suite ships.
These are tracked in the docs handoff log; they will resolve before the next docs batch.