Update README.md
Browse files
README.md
CHANGED
@@ -11,17 +11,28 @@ Link: [https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct](https://huggingface.
|
|
11 |
|
12 |
```text
|
13 |
"quantization_config": {
|
|
|
14 |
"bits": 4,
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
|
|
|
|
|
|
|
|
|
|
18 |
"group_size": 128,
|
19 |
-
"
|
20 |
-
"
|
|
|
|
|
|
|
21 |
"quant_method": "gptq",
|
22 |
-
"static_groups": false,
|
23 |
"sym": true,
|
24 |
-
"
|
|
|
|
|
|
|
25 |
},
|
26 |
```
|
27 |
|
|
|
11 |
|
12 |
```text
|
13 |
"quantization_config": {
|
14 |
+
"batch_size": 1,
|
15 |
"bits": 4,
|
16 |
+
"block_name_to_quantize": null,
|
17 |
+
"cache_block_outputs": true,
|
18 |
+
"damp_percent": 0.1,
|
19 |
+
"dataset": null,
|
20 |
+
"desc_act": false,
|
21 |
+
"exllama_config": {
|
22 |
+
"version": 1
|
23 |
+
},
|
24 |
"group_size": 128,
|
25 |
+
"max_input_length": null,
|
26 |
+
"model_seqlen": null,
|
27 |
+
"module_name_preceding_first_block": null,
|
28 |
+
"modules_in_block_to_quantize": null,
|
29 |
+
"pad_token_id": null,
|
30 |
"quant_method": "gptq",
|
|
|
31 |
"sym": true,
|
32 |
+
"tokenizer": null,
|
33 |
+
"true_sequential": true,
|
34 |
+
"use_cuda_fp16": false,
|
35 |
+
"use_exllama": true
|
36 |
},
|
37 |
```
|
38 |
|