darkmaniac7 commited on
Commit
338750c
·
verified ·
1 Parent(s): 4f6f7dc

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -46,5 +46,17 @@ Draft model: [Qwen3-0.6B](https://huggingface.co/darkmaniac7/TokForge-Accelerati
46
  ## Abliteration
47
  This model has been abliterated (safety filters removed) for unrestricted conversation. Use responsibly.
48
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  ## Export
50
  Converted using MNN's `llmexport` pipeline with `--quant_bit 4 --quant_block 128`.
 
46
  ## Abliteration
47
  This model has been abliterated (safety filters removed) for unrestricted conversation. Use responsibly.
48
 
49
+ ## Limitations and Intended Use
50
+
51
+ - Intended for TokForge / MNN on-device inference, especially Android phones and tablets.
52
+ - The best-known uplift for this model comes from pairing it with a small CPU draft model for speculative decoding.
53
+ - Real throughput varies by SoC, thermal state, backend, and generation length.
54
+ - This repo is a runtime bundle, not a standard Transformers training checkpoint.
55
+
56
+ ## Community
57
+
58
+ - Website: [tokforge.ai](https://tokforge.ai)
59
+ - Discord: [Join the Discord](https://discord.gg/Acv3CBtfVm)
60
+
61
  ## Export
62
  Converted using MNN's `llmexport` pipeline with `--quant_bit 4 --quant_block 128`.