Add MoBiQuant checkpoint model card

README.md

@@ -1,3 +1,61 @@
 ---
 license: apache-2.0
+language:
+- en
+tags:
+- mobiquant
+- quantization
+- mixed-precision
+- llama
 ---
+
+# MoBiQuant Checkpoints
+
+Calibrated OmniQuant and router parameters for **MoBiQuant** on four LLaMA base models.
+
+**Code:** [SimWangArizona/MoBiQuant](https://github.com/SimWangArizona/MoBiQuant)
+
+## Available checkpoints
+
+| Directory | Base model |
+|---|---|
+| `llama2-7b` | Llama-2-7B |
+| `llama3-8b` | Llama-3-8B |
+| `llama3-3b` | Llama-3.2-3B |
+| `llama3-1b` | Llama-3.2-1B |
+
+Each directory contains:
+
+- `omni_parameters.pth`: learned quantization parameters.
+- `router_parameters.pth`: learned router parameters.
+
+These are supplemental parameter checkpoints. Original pretrained model weights and tokenizer files are required separately; this repository cannot be loaded directly with `AutoModelForCausalLM.from_pretrained()`.
+
+## Quantization configuration
+
+- Weight-only quantization with 16-bit activations.
+- Group size: **128**.
+- Bit slices: **[2, 2, 2, 2]** — a 2-bit base plus three routed residual slices.
+- Routing covers Attention q/k/v/o and MLP gate/up/down projections.
+- Effective average bits depend on routing and the evaluation target; Attention is not fixed at 4 bits.
+
+## Download
+
+```python
+from huggingface_hub import snapshot_download
+
+checkpoint_dir = snapshot_download(
+    repo_id="Simwang/MoBiQuant",
+    allow_patterns=["llama3-1b/*.pth"],
+)
+```
+
+Replace `llama3-1b` with another directory above to download its parameters. See the code repository for evaluation instructions. The current directory-resume workflow additionally expects `router_stats.pth`; that file is not included in this release, so the downloaded pair alone is not a complete directory-resume bundle.
+
+## Validation and limitations
+
+All four checkpoints passed per-layer parameter restoration checks against the current MoBiQuant implementation. GPU WikiText2 sweeps are in progress; this release does not claim that all paper results have been reproduced.
+
+The implementation evaluates quantization using floating-point simulation. These files do not constitute a packed low-bit deployment format or establish inference speedups.
+
+The Apache-2.0 metadata applies to this release; obtain and use the original base models under their respective model licenses and access conditions.