Commit
•
d7307db
1
Parent(s):
9c5cef9
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,8 +15,10 @@ GGML files are for CPU + GPU inference using [chatglm.cpp](https://github.com/li
|
|
| 15 |
|
| 16 |
| Name | Quant method | Bits | Size |
|
| 17 |
|------|--------------|------|------|
|
| 18 |
-
|
|
| 19 |
-
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
# How to run in xorbits-inference
|
| 22 |
Coming soon.
|
|
|
|
| 15 |
|
| 16 |
| Name | Quant method | Bits | Size |
|
| 17 |
|------|--------------|------|------|
|
| 18 |
+
| chatglm2-ggml-q4_0.bin | q4_0 | 4 | 3.5 GB |
|
| 19 |
+
| chatglm2-ggml-q4_1.bin | q4_1 | 4 | 3.9 GB |
|
| 20 |
+
| chatglm2-ggml-q5_0.bin | q5_0 | 5 | 4.3 GB |
|
| 21 |
+
| chatglm2-ggml-q5_1.bin | q5_1 | 4 | 4.7 GB |
|
| 22 |
|
| 23 |
# How to run in xorbits-inference
|
| 24 |
Coming soon.
|