|
Download README.md from Inferact/Muse-Spark-Open-DSpark: direct link, hf CLI and curl.
- Browser
- Download file 2.12 kB
-
https://huggingface.co/Inferact/Muse-Spark-Open-DSpark/resolve/main/README.md
- Command line
-
hf download hf://Inferact/Muse-Spark-Open-DSpark/README.md
-
curl -L -o README.md https://huggingface.co/Inferact/Muse-Spark-Open-DSpark/resolve/main/README.md
2.12 kB
| license: other | |
| license_name: muse-spark-open | |
| license_link: LICENSE.md | |
| private: true | |
| # Muse-Spark-Open-DSpark | |
| DSpark speculative-decoding draft model for **meta-models/Muse-Spark-Open-816B-A42B** | |
| (816B-A42B MoE target, NVFP4). **Built with Muse Spark.** | |
| Trained with [speculators](https://github.com/vllm-project/speculators) from vllm-project. | |
| ## DSpark architecture | |
| - 5-layer decoder-only draft (hidden 8192, 128/16 attention/KV heads, FFN 16384), BF16, | |
| causal sliding-window attention (2048) | |
| - Full 202,048-token target vocabulary; frozen target LM head | |
| - Conditioned on target hidden states tapped at layers [13, 29, 45, 57, 61] plus the | |
| final hidden state | |
| - Proposes 7 tokens per step (sample-from-anchor); learned Markov confidence head (rank 512) | |
| - ~10.6 GB, 74 tensors, safetensors | |
| ## Acceptance rates | |
| Measured against [`meta-models/Muse-Spark-Open-816B-A42B-NVFP4`](https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B-NVFP4)(default chat template, reasoning effort `xhigh`), with the serving config | |
| below: 7 probabilistic draft tokens, block verification, temperature 1.0 / top-p 0.95. | |
| | Dataset | Requests | Acceptance | Tokens/cycle | | |
| |---|---:|---:|---:| | |
| | MT-Bench (chat) | 80 | 28.46% | 2.99 | | |
| | GSM8K | 1319 | 42.04% | 3.94 | | |
| | MATH-500 | 500 | 39.69% | 3.78 | | |
| | HumanEval | 164 | 37.23% | 3.61 | | |
| | MBPP | 974 | 35.24% | 3.47 | | |
| | AIME26 | 30 | 33.15% | 3.32 | | |
| | SWE-bench Pro | 731 | 23.69% | 2.66 | | |
| | SPEED-Bench (low entropy) | 512 | 24.76% | 2.73 | | |
| | BEAM 100K | 20 | 29.07% | 3.03 | | |
| | BEAM 500K | 35 | 29.85% | 3.09 | | |
| | BEAM 1M | 35 | 28.55% | 3.00 | | |
| Tokens/cycle is the mean number of tokens emitted per verification step, including the target's | |
| bonus token (acceptance length). SPEED-Bench uses the `throughput_16k` low-entropy split with | |
| inputs truncated to 10,240 tokens; BEAM requests generate 96 tokens each. | |
| ## Serving | |
| ```json | |
| {"method":"dspark","model":"<this repo>","num_speculative_tokens":7, | |
| "draft_sample_method":"probabilistic","enable_adaptive_verification":false, | |
| "rejection_sample_method":"block"} | |
| ``` | |
| Requires a Muse Spark–compatible serving runtime. | |