Commit
•
40205bf
1
Parent(s):
2c07ef5
GPT2gpt2: 4bits, gr-1, desc_act=False
Browse files- gptq_model-4bit--1g.bin +3 -0
- gptq_model-4bit--1g.safetensors +3 -0
- gptq_model-4bit-128g.bin +3 -0
- quantize_config.json +2 -2
gptq_model-4bit--1g.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac81f1a17bc63131844c16b04a0368aed5266d3cb59a0bb35fc13c816492a65
|
| 3 |
+
size 122044490
|
gptq_model-4bit--1g.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:803f08c7dc94cd4c3e8aaa0576afacb1614f70372658413afb9c77e62a2fe98f
|
| 3 |
+
size 199167736
|
gptq_model-4bit-128g.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba9449e1765835e1ae687beb7cce14f4e990e818f7e9408b23239d681e31fa68
|
| 3 |
+
size 123496434
|
quantize_config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"bits": 4,
|
| 3 |
-
"group_size":
|
| 4 |
"damp_percent": 0.01,
|
| 5 |
"desc_act": false,
|
| 6 |
"static_groups": false,
|
| 7 |
"sym": true,
|
| 8 |
"true_sequential": true,
|
| 9 |
"model_name_or_path": "gpt2GPTQ",
|
| 10 |
-
"model_file_base_name": "gptq_model-4bit
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bits": 4,
|
| 3 |
+
"group_size": -1,
|
| 4 |
"damp_percent": 0.01,
|
| 5 |
"desc_act": false,
|
| 6 |
"static_groups": false,
|
| 7 |
"sym": true,
|
| 8 |
"true_sequential": true,
|
| 9 |
"model_name_or_path": "gpt2GPTQ",
|
| 10 |
+
"model_file_base_name": "gptq_model-4bit--1g"
|
| 11 |
}
|