Archive
新模型、開放權重、多模態、語音、影像與模型架構。
最新模型
Microsoft launched Microsoft-Decision-1 on October 9. Post-trained from Qwen3.5-9B, it returns probabilities for predefined options in classification, routing, and agent action evaluation. The model is listed on Foundry and OpenRouter, but its performance and confidence calibration still need validation against real workloads.
GitHub Repo
A Firecrawl community report filed on October 8 says the default Base64 image cleanup may cross image boundaries, removing nearby text and table cells. The report includes a minimal reproduction in a self-hosted environment and a suggested fix, but the impact on released versions and the cloud service remains unconfirmed.
GitHub Repo
Ollama released v0.40.2 on October 8, fixing duplicate entries in the model list after migration of older models. Migration retains the original GGUF files to support downgrades, so engineering teams should account for disk usage and the need to re-download models if backups are deleted.
GitHub Repo
AutoGPT released Platform beta v0.8.3 on October 8, changing Ask First mode so a supervisor model reviews sandbox commands instead of prompting for each one. The update adds checks of script contents and shell login files, but coverage remains limited for indirect execution and file changes made after inspection.
GitHub Repo
An October 8 report from the Ollama community says Gemma 4 may generate only control tokens and then stop after receiving tool results with thinking disabled, causing the API to return a blank message. The proposed fix includes renderer tests, but the full failure case has not been publicly reproduced and the patch has not been merged.
GitHub Repo
Microsoft released ONNX Runtime 1.31.0 on October 9, stabilizing the model package and EPContext data interfaces while improving CPU model loading and quantized MoE execution. The release is available on PyPI, but teams using GPU plugins should verify operator schema compatibility and measure performance in their own environments.
GitHub Repo
An October 8 report from the Ollama community says the Clef reasoning model’s micro-batch size may be set to the full context length, causing memory allocation failures with default settings. The report includes logs from multiple backends and a workaround using a shorter context, but maintainers have yet to confirm or fix the issue.
最新模型
JetBrains released Mellum2.1 Thinking on October 8. It retains the 12B MoE architecture and focuses this update on reinforcement learning in real software environments. The weights are licensed under Apache 2.0, but agent evaluation results are self-reported, and quantized deployments require separate validation.
GitHub Repo
Ollama released v0.40.1 on October 7, switching Windows model manifests to regular files and adding an on-read repair mechanism for existing symlinks. This gives community reports of previously unusable model names an official release path, though recovery across different Windows environments remains to be verified.
最新模型
On October 7, Perplexity announced two open-weight late-interaction models for retrieving text, images, and visual documents. The 0.6B and 9B versions share an embedding space, allowing different-sized encoders to be used for document indexing and online queries, though their actual costs and performance on Chinese remain to be validated.
GitHub Repo
A reproduction on the October 8 Transformers development build found that a uniform frame-sampling function may return more indices than requested, including a position beyond the available frames. The case can be checked without downloading a model, but its impact on stable releases and individual model processors remains unclear.
GitHub Repo
A development-branch reproduction on October 7 suggests Whisper timestamp decoding may mishandle the two-dimensional tensors returned by `generate`, merging batch results or failing at runtime. The report includes a minimal reproduction, but the impact on released versions and any upstream fix remain unconfirmed.