最新模型

新模型、開放權重、多模態、語音、影像與模型架構。

Ollama Community Proposes Streaming Order Fix After Text-to-Tool Calls May Be Rejected by Responses Clients

A community report on October 5 says Ollama may reuse output indexes and omit a message completion event when it emits text before a tool call. The proposed fix includes regression tests but has not been merged or validated with actual model inference.

2026-10-03

GitHub Repo

Transformers Community Reports Memory Growth in Sparse Attention Indexer; Long DeepSeek-V3.2 Prompts May Exhaust GPU Memory

A reproduction on the October 5 development build found that the Lightning Indexer retains full per-attention-head scores, which may sharply increase temporary GPU memory use for long prompts. The report provides an isolated indexer test; effects on the full model and official releases remain unconfirmed.

2026-10-05

GitHub Repo

Transformers Community Reports FSDP2 Loading Memory Bug; Multi-GPU Startup May Create Duplicate Full Models

A community report involving Transformers 5.12.0 says that after enabling the CPU memory-efficient loading option, other training processes may still allocate a full model, exhausting host memory. Official documentation says the option should prevent duplicate loading across processes, but the root cause and fix status await upstream confirmation.

2026-10-05

GitHub Repo

Transformers Community Reports RoPE Precision Differences; Converting to bf16 After Loading May Amplify Long-Context Angle Errors

A reproduction case reported on October 4 indicates that converting a model to bf16 after loading may also lower the precision of RoPE frequency buffers, producing results that differ from loading directly in bf16. Maintainers closed a community patch proposal on October 5; the effect on real-model quality and next steps remain to be confirmed.

2026-10-05

GitHub Repo

Transformers Community Proposes MiniMax Precision Fix as bf16 Recurrence Decay May Shift Long-Sequence Decoding

A community reproduction posted on October 4 found that bf16 decay calculations in the development version of Transformers’ MiniMax Lightning Attention may prevent some attention heads from forgetting older information. A fix using fp32 has been proposed but not yet merged; its impact on model quality and performance remains to be validated.

2026-10-05

GitHub Repo

Ollama Community Proposes Request-Parsing Fix After Trailing JSON Noise Is Ignored and Inference Starts

A community reproduction on Ollama 0.35.1 showed that the generate endpoint may accept valid JSON followed by non-JSON text, return success, and run the model. A fix for full-request validation was proposed on October 3 but has not been merged.

2026-10-05

GitHub Repo

Ollama Community Reports MLX Mixed-Quantization Loading Defect: Successful Import May Still Fail at Inference

A community report involving Ollama 0.35.1 suggests that per-layer quantization settings for MLX models may not be applied correctly, causing tensor shape mismatches during loading. The model configuration confirms mixed-precision settings, but the root cause and the scope of impact on other models remain unconfirmed upstream.

2026-10-05

GitHub Repo

vLLM Community Reports Batch Invariance Cold-Start Bug That May Consistently Produce Incorrect Tokens on Specific Inference Paths

A reproduction on the vLLM development branch shows that, even with batch invariance enabled, model metadata caching and module import order may still change inference results. The community has proposed a fix, but it has not yet been merged; the impact on released versions and other hardware remains to be confirmed.

2026-09-27

GitHub Repo

LangChain Community Reports Retry Filter Trap: A Single Exception Class May Cause Unexpected Errors to Be Retried

A community reproduction on LangChain 1.4.0 suggests that passing an exception class directly to `retry_on` may cause models and tools to retry errors that do not match the intended filter. The official documentation calls for a tuple of exception classes or a predicate function; a fix and the full scope of impact remain unconfirmed.

2026-10-04

GitHub Repo

Transformers Community Reports Tokenizer Configuration Mismatch That May Silently Drop Chinese Input in DeepSeek Models

A reproduction on Transformers 5.8.1 suggests that certain DeepSeek models may load the wrong tokenization pipeline, causing Chinese input to disappear and English spaces to be lost. Current development-branch documentation describes a fallback for configuration mismatches, but whether this case is fixed across versions remains unconfirmed.

2026-10-04

GitHub Repo

Ollama Community Reports Missing Text in LFM2 Output; Certain Python Strings May Disappear Silently

A community reproduction on Ollama 0.35.1 suggests that `lfm2:24b` may omit certain Python strings, altering JSON values and document content. Upstream has yet to confirm the issue, and there is not enough evidence to determine whether it stems from tokenizer decoding, model packaging, or the hardware path.

2026-10-04

Ai2 Releases AstaBrief 8B, Simplifying Citation-Backed Scientific Reporting in a Single Generation

Built on Qwen3-8B, AstaBrief releases model weights and training data, combining research questions and retrieved passages into reports. Ai2 reports that the end-to-end workflow is about 3.5× faster, though the comparison mainly uses models and evaluations from 2025.

2026-10-04