Hugging Face's logo

ModelCloud
/
Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-v1

Text Generation
Safetensors
English
qwen2
gptqmodel
modelcloud
code
codeqwen
chat
qwen
qwen-coder
instruct
int4
gptq
4bit
conversational
4-bit precision
Model card Files Community
4
lrl-modelcloud commited on
Commit
61e6721
•
1 Parent(s): b6d9041

Upload folder using huggingface_hub (#3)

Browse files

- e8567040d4a4206b13a8a501bd7f59c78fa5cd5109dae64383cfb1db73610cbf (dfe42b890d8ea51c536ea5b9f977a102100b9edf)
- 731b4cdacd3b30f051103012ac3f9b7e6388237261e2ddabd5948f62f7e00eb6 (619c731aeaceb80705d9bcee5e5f1dcf538045c2)
- c95f793f89216c6a3ffbd8842c305185090cf8ed74f11f21a8984af6b7d9008f (0f65e6e263e0c61820f0a2fc0a507f004a04517c)
- 537e527a138486e6b9201f385d34c679d14eb968a0ed8dd8d972176e1a6943b9 (240605ec337e64bb45454a3f4e640949d95e4359)
- 4df5a7a0bd69535850cffe72de19325d4055502e3e17d0e8d428fb72f63df45e (dc681348cf7c6cc090724a34b21b2e5ea107c0f3)
- 022ad0d97a033fa0cd70bfa00f177b7490843657f17207814a4b8888b1be0c14 (2c8a01187b0365e17c11da9016df073ab13c9d8f)

Files changed (9) hide show
  1. config.json +5 -3
  2. model-00001-of-00006.safetensors +3 -0
  3. model-00002-of-00006.safetensors +3 -0
  4. model-00003-of-00006.safetensors +3 -0
  5. model-00004-of-00006.safetensors +3 -0
  6. model-00005-of-00006.safetensors +3 -0
  7. model-00006-of-00006.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. quantize_config.json +4 -2
config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": true,
3
- "_name_or_path": "/monster/data/model/Qwen2.5-Coder-32B-Instruct",
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": 0.1,
30
- "quantizer": "gptqmodel:1.2.1",
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-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c26d93cd0d4ccce97c738c7b5ba01c90722300954863f55753ab6c8d17dfa6
3
+ size 3932734920
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8042372a5f9540504a4b2dec4a04023148f3f48b9d32e4e6043cc139ae2e3e39
3
+ size 3950222264
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2aff54876644a0f3467754d84af25829c37ba4c093fe84485a7c6749dd1ac2
3
+ size 3950222320
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e12abfa7617c2678b67cafd9c4e4a2f2c6c46547d4dc8cea1a0c51c67ba35e
3
+ size 3950222320
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dce89b1734b0f38803a0cac1e456e3ccff7bfdc544caa995266f616ffe84a77
3
+ size 3831902736
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:1.2.1",
14
  "uri": "https://github.com/modelcloud/gptqmodel",
15
- "damp_percent": 0.1,
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
  }