Commit
•
2c8a011
1
Parent(s):
dc68134
022ad0d97a033fa0cd70bfa00f177b7490843657f17207814a4b8888b1be0c14
Browse files- config.json +5 -3
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantize_config.json +4 -2
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_attn_implementation_autoset": true,
|
| 3 |
-
"_name_or_path": "/monster/data/
|
| 4 |
"architectures": [
|
| 5 |
"Qwen2ForCausalLM"
|
| 6 |
],
|
|
@@ -20,14 +20,16 @@
|
|
| 20 |
"quantization_config": {
|
| 21 |
"bits": 4,
|
| 22 |
"checkpoint_format": "gptq",
|
|
|
|
|
|
|
| 23 |
"desc_act": true,
|
| 24 |
"dynamic": null,
|
| 25 |
"group_size": 32,
|
| 26 |
"lm_head": false,
|
| 27 |
"meta": {
|
| 28 |
"damp_auto_increment": 0.0015,
|
| 29 |
-
"damp_percent": 0.
|
| 30 |
-
"quantizer": "gptqmodel:1.2.
|
| 31 |
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 32 |
},
|
| 33 |
"quant_method": "gptq",
|
|
|
|
| 1 |
{
|
| 2 |
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "/monster/data/lrl/qwen2.5_coder_32b_quant/Q_upload/",
|
| 4 |
"architectures": [
|
| 5 |
"Qwen2ForCausalLM"
|
| 6 |
],
|
|
|
|
| 20 |
"quantization_config": {
|
| 21 |
"bits": 4,
|
| 22 |
"checkpoint_format": "gptq",
|
| 23 |
+
"damp_auto_increment": 0.0015,
|
| 24 |
+
"damp_percent": 0.005,
|
| 25 |
"desc_act": true,
|
| 26 |
"dynamic": null,
|
| 27 |
"group_size": 32,
|
| 28 |
"lm_head": false,
|
| 29 |
"meta": {
|
| 30 |
"damp_auto_increment": 0.0015,
|
| 31 |
+
"damp_percent": 0.005,
|
| 32 |
+
"quantizer": "gptqmodel:1.2.0-dev",
|
| 33 |
"uri": "https://github.com/modelcloud/gptqmodel"
|
| 34 |
},
|
| 35 |
"quant_method": "gptq",
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ee0a67819e99d588a47b9c51ce3a3b3b819d7b007f8acfe8c1179b1db7a55be
|
| 3 |
+
size 1557135488
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantize_config.json
CHANGED
|
@@ -6,13 +6,15 @@
|
|
| 6 |
"static_groups": false,
|
| 7 |
"sym": true,
|
| 8 |
"lm_head": false,
|
|
|
|
|
|
|
| 9 |
"true_sequential": true,
|
| 10 |
"quant_method": "gptq",
|
| 11 |
"checkpoint_format": "gptq",
|
| 12 |
"meta": {
|
| 13 |
-
"quantizer": "gptqmodel:1.2.
|
| 14 |
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
-
"damp_percent": 0.
|
| 16 |
"damp_auto_increment": 0.0015
|
| 17 |
}
|
| 18 |
}
|
|
|
|
| 6 |
"static_groups": false,
|
| 7 |
"sym": true,
|
| 8 |
"lm_head": false,
|
| 9 |
+
"damp_percent": 0.005,
|
| 10 |
+
"damp_auto_increment": 0.0015,
|
| 11 |
"true_sequential": true,
|
| 12 |
"quant_method": "gptq",
|
| 13 |
"checkpoint_format": "gptq",
|
| 14 |
"meta": {
|
| 15 |
+
"quantizer": "gptqmodel:1.2.0-dev",
|
| 16 |
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 17 |
+
"damp_percent": 0.005,
|
| 18 |
"damp_auto_increment": 0.0015
|
| 19 |
}
|
| 20 |
}
|