Update README.md
Browse files
README.md
CHANGED
@@ -5,14 +5,16 @@ license: unknown
|
|
5 |
This is TinyLlama/TinyLlama-1.1B-Chat-v1.0 quantized with AutoGPTQ in GPTQ 4-bit Marlin format.
|
6 |
|
7 |
**Quantize config:**
|
8 |
-
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"quant_method": "gptq"
|
|
|
|
|
|
5 |
This is TinyLlama/TinyLlama-1.1B-Chat-v1.0 quantized with AutoGPTQ in GPTQ 4-bit Marlin format.
|
6 |
|
7 |
**Quantize config:**
|
8 |
+
```
|
9 |
+
"bits": 4,
|
10 |
+
"group_size": 128,
|
11 |
+
"damp_percent": 0.01,
|
12 |
+
"desc_act": false,
|
13 |
+
"static_groups": false,
|
14 |
+
"sym": true,
|
15 |
+
"true_sequential": true,
|
16 |
+
"model_name_or_path": null,
|
17 |
+
"model_file_base_name": null,
|
18 |
+
"quant_method": "gptq",
|
19 |
+
"checkpoint_format": "marlin"
|
20 |
+
```
|