v0.32.12: qwen3.8: add renderer and MLX import support
Artikelbild eller återanvändbart omslag för Ollama
Qwen3.8 keeps the Qwen3.5 model architecture and parser, but its chat template adds reasoning-effort and preserved-thinking semantics.
Detect those template markers during safetensors import, select the qwen3.8 renderer, and cover thinking, tools, continuation, and malformed parser input. Make indexed safetensors imports use the weight map's shard names instead of independently filtering files by the model-* convention. Reject unsafe shard paths, ignore unindexed tensors, and fail when an indexed weight is missing or stored in a different shard. Retain the conservative model-* scan when no index is present. Treat Classification.Quantize as the effective tensor format and pass it to the manifest writer. This records file_type for automatic block-FP8-to-MXFP8 conversion and recognized prequantized inputs, preserves requested quantization and base-plus-draft behavior, and avoids claiming one type for mixed or unknown formats. Normalize both supported convolution weight layouts with an explicit reshape.
Texten är källans egen beskrivning av publiceringen. Innehållet tillhör Ollama.
Mer att läsa
Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation
Techmeme för 2 tim sedan
DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions
Techmeme för 2 tim sedan
Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash
Techmeme för 2 tim sedan
One word for AI agents in 2027
Nate Herk för 6 tim sedan