Hybrid Turkish LLM research: replacing 20% of Qwen3-14B softmax attention layers with Gated DeltaNet, with reproducible benchmarks and confidence intervals.

0 stars 0 forks 0 watchers Python Apache License 2.0
efficient-attention gated-deltanet large-language-models linear-attention llm-research open-source-ai pytorch qwen3 transformers turkish-nlp
3 Open Issues Need Help Last updated: Jul 30, 2026

Open Issues Need Help

View All on GitHub
help wanted research question measurement

Hybrid Turkish LLM research: replacing 20% of Qwen3-14B softmax attention layers with Gated DeltaNet, with reproducible benchmarks and confidence intervals.

Python
#efficient-attention#gated-deltanet#large-language-models#linear-attention#llm-research#open-source-ai#pytorch#qwen3#transformers#turkish-nlp
help wanted research question measurement

Hybrid Turkish LLM research: replacing 20% of Qwen3-14B softmax attention layers with Gated DeltaNet, with reproducible benchmarks and confidence intervals.

Python
#efficient-attention#gated-deltanet#large-language-models#linear-attention#llm-research#open-source-ai#pytorch#qwen3#transformers#turkish-nlp
help wanted research question measurement

Hybrid Turkish LLM research: replacing 20% of Qwen3-14B softmax attention layers with Gated DeltaNet, with reproducible benchmarks and confidence intervals.

Python
#efficient-attention#gated-deltanet#large-language-models#linear-attention#llm-research#open-source-ai#pytorch#qwen3#transformers#turkish-nlp