darkmaniac7
/

TokForge-AccelerationPack-Qwen35-Draft

Text Generation

speculative-decoding

Model card Files Files and versions

TokForge-AccelerationPack-Qwen35-Draft

484 MB

Ctrl+K

Ctrl+K

1 contributor

History: 13 commits

darkmaniac7's picture

Add TokForge app links

2683925 verified 1 day ago

.gitattributes

1.66 kB
fix: replace VL model with text-only abliterated (prevents spec decode crash) 4 months ago
README.md

2.09 kB
Add TokForge app links 1 day ago
config.json

342 Bytes
feat: abliterated 0.8B with fixed graph (no FusedLinearAttention ops, is_visual=false) 4 months ago
export_args.json

1.11 kB
feat: abliterated 0.8B with fixed graph (no FusedLinearAttention ops, is_visual=false) 4 months ago
llm.mnn

2.15 MB
xet

feat: abliterated 0.8B with fixed graph (no FusedLinearAttention ops, is_visual=false) 4 months ago
llm.mnn.json

5.34 MB
xet

feat: abliterated 0.8B with fixed graph (no FusedLinearAttention ops, is_visual=false) 4 months ago
llm.mnn.weight

470 MB
xet

feat: abliterated 0.8B with fixed graph (no FusedLinearAttention ops, is_visual=false) 4 months ago
llm_config.json

8.69 kB
fix: is_visual=false + original taobao graph (was broken 320KB graph). 80% acceptance, +49% on 9B. 4 months ago
tokenizer.txt

6.47 MB
Upload folder using huggingface_hub 4 months ago