Upload README.md with huggingface_hub

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: openbmb/MiniCPM5-1B
 tags:
+- speculative-decoding-draft
   - dispatch-ai
   - mobile
   - quantized
@@ -46,3 +47,38 @@ Tested on **Samsung Galaxy S20 FE 5G** (Snapdragon 865, 8GB RAM):
 ```
 
 🌐 [dispatchAI on HuggingFace](https://huggingface.co/dispatchAI)
+
+
+## Speculative Decoding Draft Model
+
+This model is optimized for use as a **draft model** in speculative decoding setups.
+
+### What is speculative decoding?
+Speculative decoding pairs a small, fast "draft" model with a larger "target" model.
+The draft model proposes tokens that the target model verifies in parallel, achieving
+2-3x speedup with zero quality loss.
+
+### Why this model?
+- **Small and fast**: Sub-1B parameters = minimal draft overhead
+- **Mobile-optimized**: Already quantized and pruned for edge deployment
+- **Same family**: Pairs naturally with larger models of the same architecture
+
+### Usage with vLLM
+```python
+from vllm import LLM, SamplingParams
+
+llm = LLM(
+    model="target-model-7b",
+    speculative_model="dispatchAI/MiniCPM5-1B-mobile",
+    num_speculative_tokens=5,
+)
+```
+
+### Usage with transformers
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+target = AutoModelForCausalLM.from_pretrained("target-model-7b")
+draft = AutoModelForCausalLM.from_pretrained("dispatchAI/MiniCPM5-1B-mobile")
+# See transformers docs for assisted_generation
+```