Add TokForge app links
3c53adc verified - 1.61 kB Upload folder using huggingface_hub
- 5.27 kB Add TokForge app links
- 211 Bytes v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
- 211 Bytes v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
- 172 Bytes Add config_opencl.json for OpenCL draft backend support
- 211 Bytes v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
- 504 kB v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
- 1.01 MB Upload llm.mnn.json with huggingface_hub
- 336 MB v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
- 4.66 kB v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
- 1.36 kB Add runtime_config.json with optimal spec decode settings
- 1.61 MB v3: KL-distilled 0.6B from Qwen3-8B (10K samples, KL=0.339, +41% uplift on SM8850)
