No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from RedHatAI/Qwen3.6-35B-A3B-speculator.dspark
All models by RedHatAI βThis is a DSpark speculator model for Qwen/Qwen3.6-35B-A3B.
This model was trained using the Speculators library library on a subset of Magpie-Align/Magpie-Llama-3.1-Pro-300K-Filtered and the train_sft split of HuggingFaceH4/ultrachat_200k. Responses were regenerated by Qwen3.6-35B-A3B. DSpark extends DFlash with a Markov head (intra-block token dependency) and a confidence head (per-position acceptance prediction). Training compute for this model was generously provided by Lambda, a leading cloud platform for AI training and inference.
Using the Speculators library and the helper scripts provided in the repo.
Must be run once vLLM has finished launching and is running in the background.
Per-position token acceptance rates across datasets:
# In virtual environment with speculators installedpython scripts/prepare_data.py \ --model Qwen/Qwen3.6-35B-A3B \ --data ./data/qwen3_6_35b_a3b_regen/magpie_output.jsonl \ --data ./data/qwen3_6_35b_a3b_regen/ultrachat_output.jsonl \ --output ./output/dspark_qwen3_6_35b_a3b \ --seq-length 16000# In (separate) virtual environment with vllm installedCUDA_VISIBLE_DEVICES=0,1,2,3 python scripts/launch_vllm.py \ Qwen/Qwen3.6-35B-A3B \ --target-layer-ids 2 10 20 30 37 \ -- --port 8000 \ --tensor-parallel-size 4 \ --max-model-len 16002 \ --enforce-eager# In virtual environment with speculators installedCUDA_VISIBLE_DEVICES=4,5,6,7 torchrun \ --standalone \ --nproc_per_node 4 \ scripts/train.py \ --verifier-name-or-path Qwen/Qwen3.6-35B-A3B \ --speculator-type dspark \ --data-path ./output/dspark_qwen3_6_35b_a3b \ --vllm-endpoint http://localhost:8000/v1 \ --save-path ./output/dspark_qwen3_6_35b_a3b/checkpoints \ --block-size 8 \ --max-anchors 3072 \ --target-layer-ids 2 10 20 30 37 \ --num-layers 5 \ --markov-rank 256 \ --markov-head-type vanilla \ --enable-confidence-head \ --confidence-head-with-markov \ --loss-fn '{"ce": 0.1, "tv": 0.9}' \ --confidence-head-alpha 1.0 \ --epochs 5 \ --lr 3e-4 \ --total-seq-len 16000 \ --on-missing generate \ --on-generate delete \ --checkpoint-freq 0.1# Deploy with speculative decodingvllm serve Qwen/Qwen3.6-35B-A3B \ --tensor-parallel-size 2 \ --speculative-config '{ "model": "RedHatAI/Qwen3.6-35B-A3B-speculator.dspark", "num_speculative_tokens": 8, "method": "dspark" }'