Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
darkmaniac7
/
TokForge-AccelerationPack-Draft
like
0
Text Generation
English
mnn
speculative-decoding
draft-model
qwen3
tokforge
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
TokForge-AccelerationPack-Draft
339 MB
Ctrl+K
Ctrl+K
1 contributor
History:
14 commits
darkmaniac7
Upload llm.mnn.json with huggingface_hub
e20d0d7
verified
2 months ago
.gitattributes
Safe
1.61 kB
Upload folder using huggingface_hub
3 months ago
README.md
Safe
5 kB
Upload README.md with huggingface_hub
3 months ago
config.json
Safe
211 Bytes
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
config_cpu.json
Safe
211 Bytes
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
config_opencl.json
Safe
172 Bytes
Add config_opencl.json for OpenCL draft backend support
3 months ago
draft_config_cpu.json
Safe
211 Bytes
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
llm.mnn
504 kB
xet
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
llm.mnn.json
Safe
1.01 MB
Upload llm.mnn.json with huggingface_hub
2 months ago
llm.mnn.weight
336 MB
xet
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
llm_config.json
Safe
4.66 kB
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
runtime_config.json
Safe
1.36 kB
Add runtime_config.json with optimal spec decode settings
3 months ago
tokenizer.txt
Safe
1.61 MB
v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
3 months ago
