Aquesta és una versió anterior. La versió actual és la 0.27.8. Transformer Lab 0.27.8 · Data de publicació:
Fitxers d’instal·lació 0.11.2
| Arquitectura | Tipus | Àmbit | Mida del fitxer | Baixa | SHA256 |
|---|---|---|---|---|---|
| 64 bits | EXE (NSIS) | Usuari actual | — | github.com | VirusTotal |
L’enllaç i l’SHA256 provenen del manifest comunitari del Gestor de paquets del Windows. Convé comparar el hash del fitxer baixat abans d’executar-lo.
Notes de la versió
Highlights
- AirLLM for MLX: run models larger than your available GPU memory!
- Fastchat server: Gemma3 support, and Evaluate logprobs now works
- Embeddings: correctly uses selected embedding model, several fixes to training plugin
- Ollama Server is the now the default server plugin for users without a GPU or MLX
Specific additions to Evaluations:
- Custom evals: create your own evals using custom python code
- Red Teaming Plugin: generate detailed reports of potential vulnerabilities in your LLMs
- GEval: Enter a description to DeepEval LLM-as-Judge to create an evaluation metric for you automatically
Full github notes
- Add GEval Widget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/324
- Change Process Embeddings to use in-built embeddings function by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/323
- Change string comparison to exact equals to prevent collision issues by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/325
- Fixes reset to default embedding and adds embedding to experiment json on new setup by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/327
- Remove ipc for darkmode (it wasn't used) by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/326
- Remove under construction message from visualize logprobs by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/328
- Add option for Code return type in the widget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/332
- Fix/screen-size-adjustments-for-cloud by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/331
- I don't think preload-cloud was actually doing anything by @aliasaria in https://github.com/transformerlab/transformerlab-app/pull/330
- Divide evals menu in dataset-based and model-based by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/334
- Add Azure OpenAI option in settings and enable in ModelProviderWidget by @deep1401 in https://github.com/transformerlab/transformerlab-app/pull/338
Full Changelog: https://github.com/transformerlab/transformerlab-app/compare/v0.11.1...v0.11.2https://github.com/transformerlab/transformerlab-app/releases/tag/v0.11.2
