CoolFace
17 results

inference-optimization

inallmodelsdatasetsappsagentspeopleprojects

Models

All models matching “inference-optimization”
inference-optimization /Llama-3.2-0.5B-Instructtext-generationtransformers1 likes25k downloads4mo agoHugging Faceinference-optimization /Qwen3-1.6B-A0.9Btext-generationtransformers3 likes16k downloads4mo agoHugging Faceinference-optimization /Qwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1speculators0 likes7.7k downloads3mo agoHugging Faceinference-optimization /Qwen3-8B-speculators.peagle-qwen3arch-ckpt4speculators1 likes7.7k downloads3mo agoHugging Faceinference-optimization /Qwen3-Coder-Next.w4a16text-generation1 likes6.6k downloads6mo agoHugging Faceinference-optimization /GLM-5.2-0.8B-A0.8Btext-generationtransformers4 likes5.4k downloads3mo agoHugging Faceinference-optimization /DSV4-tiny-empty1 likes5.4k downloads7d agoHugging Faceinference-optimization /DeepSeek-V3-debug-empty-FP8_DYNAMIC0 likes5.3k downloads8mo agoHugging Face

Datasets

All datasets matching “inference-optimization”
inference-optimization /speculators-ci-datasets speculator-tutorial Raw vs. on-policy regenerated conversation data for training speculative-decoding drafters (EAGLE-3 / DFlash / DSpark style), with the original source data kept alongside so you can see exactly what regeneration changes and why it matters. Prompts come from UltraChat-200k. The verifier / teacher model is Qwen/Qwen3-8B. Why regenerate at all? A speculative-decoding drafter is trained to predict what the verifier would say next. If you train it… See the full description on the dataset page: https://huggingface.co/datasets/inference-optimization/speculators-ci-datasets.tabulartext-generation1K<n<10K0 likes1.1k downloads1mo agoHugging Faceinference-optimization /Qwen3-8B-Regenerated-Collection0 likes211 downloads4mo agoHugging Faceinference-optimization /speculators_benchmarks_tool_calltext1K<n<10K1 likes185 downloads5mo agoHugging Faceinference-optimization /dflash-code-multilingual-teacher-responses-qwen235b Code + Multilingual Teacher Responses (Qwen3-235B-A22B-Instruct-2507) This repo now contains 302,800 total samples across the main blended data.jsonl / .parquet file plus a second Nemotron-only file (nemotron_code_teacher_responses.jsonl / .parquet). All responses were generated by Qwen3-235B-A22B-Instruct-2507 in non-thinking mode (enable_thinking=false) to match downstream speculator training and eval. Built in two batches: an initial 59,506-row batch (50K code + 9.5K… See the full description on the dataset page: https://huggingface.co/datasets/inference-optimization/dflash-code-multilingual-teacher-responses-qwen235b.texttext-generation100K<n<1M1 likes171 downloads20d agoHugging Faceinference-optimization /Qwen3.5-0.8B-responsestext1K<n<10K0 likes149 downloads4mo agoHugging Faceinference-optimization /Qwen3-30B-A3B-responses0 likes138 downloads4mo agoHugging Face

Apps

All apps matching “inference-optimization”
KennyLaw /voice-conversational-ai-inference-optimizationstatic0 likes9mo agoHugging Facenareshns2004 /GPU-Inference-Optimization-Labstatic0 likes1mo agoHugging Facevireshk /LLM-Inference-Optimizationstatic0 likes9h agoHugging Face