aoiandroid's picture
Upload README.md with huggingface_hub
16649fa verified
|
Raw
History Blame Contribute Delete
670 Bytes
---
base_model: meta-llama/Llama-3.2-1B-Instruct
license: llama3.2
tags:
- coreml
- llama
- kv-cache
- stateful
---
# Llama 3.2 1B — Stateful KV Cache Core ML (unified model)
Single **unified** Core ML bundle: `input_ids`, `causal_mask`, state `keyCache` / `valueCache`.
## Structure
```
ctx{N}_fp16/Llama32_1B_KVCache/ — FP16 unified model
ctx{N}_int4/Llama32_1B_KVCache/ — INT4 unified model (optional)
```
## Usage
- **OS**: macOS 15 / iOS 18+
- **Compute units**: CPU_AND_GPU
- **Inference**: `make_state()`; prefill + decode with the same model; see notebook Step 9 for `causal_mask` shapes.
Memory estimate (FP16 KV): 0.00 GB for ctx=4096.