Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ tags:
|
|
| 19 |
- yarn
|
| 20 |
---
|
| 21 |
|
| 22 |
-
# Hy3-
|
| 23 |
|
| 24 |
A **4-bit weight-only (W4A16)** quantization of **[tencent/Hy3](https://huggingface.co/tencent/Hy3)**
|
| 25 |
(`HYV3ForCausalLM`, `hy_v3`) — a 295B-parameter / 21B-active Mixture-of-Experts model.
|
|
|
|
| 19 |
- yarn
|
| 20 |
---
|
| 21 |
|
| 22 |
+
# Hy3-1M — 4-bit (INT4) quantization of tencent/Hy3 for 1M context
|
| 23 |
|
| 24 |
A **4-bit weight-only (W4A16)** quantization of **[tencent/Hy3](https://huggingface.co/tencent/Hy3)**
|
| 25 |
(`HYV3ForCausalLM`, `hy_v3`) — a 295B-parameter / 21B-active Mixture-of-Experts model.
|