Update README.md
Browse files
README.md
CHANGED
|
@@ -15,10 +15,9 @@ base_model:
|
|
| 15 |
- **Operating System(s):** Linux
|
| 16 |
- **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
|
| 17 |
- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (V0.12)
|
| 18 |
-
- **Weight quantization:**
|
| 19 |
-
- **Activation quantization:** OCP MXFP4
|
| 20 |
-
- **
|
| 21 |
-
- **Excluded from quantization:** `self_attn` weights kept at FP8, MoE gates, `lm_head`, vision tower and multimodal projector kept at BF16
|
| 22 |
|
| 23 |
This model was built with the Kimi-K2.7-Code model by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for MXFP4 quantization.
|
| 24 |
|
|
|
|
| 15 |
- **Operating System(s):** Linux
|
| 16 |
- **Inference Engine:** [vLLM](https://docs.vllm.ai/en/latest/)
|
| 17 |
- **Model Optimizer:** [AMD-Quark](https://quark.docs.amd.com/latest/index.html) (V0.12)
|
| 18 |
+
- **Weight quantization:** OCP MXFP4, Static; self_attn Perchannel, FP8E4M3, Static
|
| 19 |
+
- **Activation quantization:** OCP MXFP4, Dynamic; self_attn FP8E4M3, per-channel, Dynamic
|
| 20 |
+
- **Excluded from quantization:** MoE gates, `lm_head`, vision tower and multimodal projector
|
|
|
|
| 21 |
|
| 22 |
This model was built with the Kimi-K2.7-Code model by applying [AMD-Quark](https://quark.docs.amd.com/latest/index.html) for MXFP4 quantization.
|
| 23 |
|