Hugging Face's logo

ModelCloud
/
GLM-4.6-GPTQMODEL-W4A16-v1

Text Generation
Safetensors
English
glm4_moe
gptqmodel
modelcloud
chat
glm4.6
glm
instruct
int4
gptq
4bit
w4a16
conversational
4-bit precision
Model card Files
xet
Community
Qubitium commited on
Commit
a6148e5
·
verified ·
1 Parent(s): 53072b3

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. chat_template.jinja +103 -0
  3. config.json +68 -0
  4. generation_config.json +11 -0
  5. model-00001-of-00049.safetensors +3 -0
  6. model-00003-of-00049.safetensors +3 -0
  7. model-00004-of-00049.safetensors +3 -0
  8. model-00005-of-00049.safetensors +3 -0
  9. model-00006-of-00049.safetensors +3 -0
  10. model-00008-of-00049.safetensors +3 -0
  11. model-00009-of-00049.safetensors +3 -0
  12. model-00010-of-00049.safetensors +3 -0
  13. model-00011-of-00049.safetensors +3 -0
  14. model-00012-of-00049.safetensors +3 -0
  15. model-00013-of-00049.safetensors +3 -0
  16. model-00014-of-00049.safetensors +3 -0
  17. model-00015-of-00049.safetensors +3 -0
  18. model-00016-of-00049.safetensors +3 -0
  19. model-00017-of-00049.safetensors +3 -0
  20. model-00019-of-00049.safetensors +3 -0
  21. model-00020-of-00049.safetensors +3 -0
  22. model-00021-of-00049.safetensors +3 -0
  23. model-00022-of-00049.safetensors +3 -0
  24. model-00023-of-00049.safetensors +3 -0
  25. model-00024-of-00049.safetensors +3 -0
  26. model-00026-of-00049.safetensors +3 -0
  27. model-00028-of-00049.safetensors +3 -0
  28. model-00029-of-00049.safetensors +3 -0
  29. model-00030-of-00049.safetensors +3 -0
  30. model-00031-of-00049.safetensors +3 -0
  31. model-00032-of-00049.safetensors +3 -0
  32. model-00033-of-00049.safetensors +3 -0
  33. model-00034-of-00049.safetensors +3 -0
  34. model-00035-of-00049.safetensors +3 -0
  35. model-00037-of-00049.safetensors +3 -0
  36. model-00038-of-00049.safetensors +3 -0
  37. model-00039-of-00049.safetensors +3 -0
  38. model-00040-of-00049.safetensors +3 -0
  39. model-00041-of-00049.safetensors +3 -0
  40. model-00042-of-00049.safetensors +3 -0
  41. model-00044-of-00049.safetensors +3 -0
  42. model-00045-of-00049.safetensors +3 -0
  43. model-00046-of-00049.safetensors +3 -0
  44. model-00047-of-00049.safetensors +3 -0
  45. model-00049-of-00049.safetensors +3 -0
  46. model.safetensors.index.json +3 -0
  47. quant_log.csv +0 -0
  48. quantize_config.json +25 -0
  49. special_tokens_map.json +34 -0
  50. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- if tools -%}
3
+ <|system|>
4
+ # Tools
5
+
6
+ You may call one or more functions to assist with the user query.
7
+
8
+ You are provided with function signatures within <tools></tools> XML tags:
9
+ <tools>
10
+ {% for tool in tools %}
11
+ {{ tool | tojson(ensure_ascii=False) }}
12
+ {% endfor %}
13
+ </tools>
14
+
15
+ For each function call, output the function name and arguments within the following XML format:
16
+ <tool_call>{function-name}
17
+ <arg_key>{arg-key-1}</arg_key>
18
+ <arg_value>{arg-value-1}</arg_value>
19
+ <arg_key>{arg-key-2}</arg_key>
20
+ <arg_value>{arg-value-2}</arg_value>
21
+ ...
22
+ </tool_call>{%- endif -%}
23
+ {%- macro visible_text(content) -%}
24
+ {%- if content is string -%}
25
+ {{- content }}
26
+ {%- elif content is iterable and content is not mapping -%}
27
+ {%- for item in content -%}
28
+ {%- if item is mapping and item.type == 'text' -%}
29
+ {{- item.text }}
30
+ {%- elif item is string -%}
31
+ {{- item }}
32
+ {%- endif -%}
33
+ {%- endfor -%}
34
+ {%- else -%}
35
+ {{- content }}
36
+ {%- endif -%}
37
+ {%- endmacro -%}
38
+ {%- set ns = namespace(last_user_index=-1) %}
39
+ {%- for m in messages %}
40
+ {%- if m.role == 'user' %}
41
+ {% set ns.last_user_index = loop.index0 -%}
42
+ {%- endif %}
43
+ {%- endfor %}
44
+ {% for m in messages %}
45
+ {%- if m.role == 'user' -%}<|user|>
46
+ {{ visible_text(m.content) }}
47
+ {{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
48
+ {%- elif m.role == 'assistant' -%}
49
+ <|assistant|>
50
+ {%- set reasoning_content = '' %}
51
+ {%- set content = visible_text(m.content) %}
52
+ {%- if m.reasoning_content is string %}
53
+ {%- set reasoning_content = m.reasoning_content %}
54
+ {%- else %}
55
+ {%- if '</think>' in content %}
56
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
57
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {%- if loop.index0 > ns.last_user_index and reasoning_content -%}
61
+ {{ '\n<think>' + reasoning_content.strip() + '</think>'}}
62
+ {%- else -%}
63
+ {{ '\n<think></think>' }}
64
+ {%- endif -%}
65
+ {%- if content.strip() -%}
66
+ {{ '\n' + content.strip() }}
67
+ {%- endif -%}
68
+ {% if m.tool_calls %}
69
+ {% for tc in m.tool_calls %}
70
+ {%- if tc.function %}
71
+ {%- set tc = tc.function %}
72
+ {%- endif %}
73
+ {{ '\n<tool_call>' + tc.name }}
74
+ {% set _args = tc.arguments %}
75
+ {% for k, v in _args.items() %}
76
+ <arg_key>{{ k }}</arg_key>
77
+ <arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
78
+ {% endfor %}
79
+ </tool_call>{% endfor %}
80
+ {% endif %}
81
+ {%- elif m.role == 'tool' -%}
82
+ {%- if m.content is string -%}
83
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
84
+ {{- '<|observation|>' }}
85
+ {%- endif %}
86
+ {{- '\n<tool_response>\n' }}
87
+ {{- m.content }}
88
+ {{- '\n</tool_response>' }}
89
+ {%- else -%}
90
+ <|observation|>{% for tr in m.content %}
91
+
92
+ <tool_response>
93
+ {{ tr.output if tr.output is defined else tr }}
94
+ </tool_response>{% endfor -%}
95
+ {% endif -%}
96
+ {%- elif m.role == 'system' -%}
97
+ <|system|>
98
+ {{ visible_text(m.content) }}
99
+ {%- endif -%}
100
+ {%- endfor -%}
101
+ {%- if add_generation_prompt -%}
102
+ <|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
103
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4MoeForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": [
9
+ 151329,
10
+ 151336,
11
+ 151338
12
+ ],
13
+ "first_k_dense_replace": 3,
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 5120,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 12288,
19
+ "max_position_embeddings": 202752,
20
+ "model_type": "glm4_moe",
21
+ "moe_intermediate_size": 1536,
22
+ "n_group": 1,
23
+ "n_routed_experts": 160,
24
+ "n_shared_experts": 1,
25
+ "norm_topk_prob": true,
26
+ "num_attention_heads": 96,
27
+ "num_experts_per_tok": 8,
28
+ "num_hidden_layers": 92,
29
+ "num_key_value_heads": 8,
30
+ "num_nextn_predict_layers": 1,
31
+ "pad_token_id": 151329,
32
+ "partial_rotary_factor": 0.5,
33
+ "quantization_config": {
34
+ "bits": 4,
35
+ "checkpoint_format": "gptq",
36
+ "desc_act": false,
37
+ "group_size": 32,
38
+ "lm_head": false,
39
+ "meta": {
40
+ "act_group_aware": true,
41
+ "damp_auto_increment": 0.01,
42
+ "damp_percent": 0.05,
43
+ "mse": 0.0,
44
+ "quantizer": [
45
+ "gptqmodel:5.0.0-dev0"
46
+ ],
47
+ "static_groups": false,
48
+ "true_sequential": true,
49
+ "uri": "https://github.com/modelcloud/gptqmodel",
50
+ "v2": false,
51
+ "v2_alpha": 0.25
52
+ },
53
+ "pack_dtype": "int32",
54
+ "pack_impl": "cpu",
55
+ "quant_method": "gptq",
56
+ "sym": true
57
+ },
58
+ "rms_norm_eps": 1e-05,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000,
61
+ "routed_scaling_factor": 2.5,
62
+ "tie_word_embeddings": false,
63
+ "topk_group": 1,
64
+ "transformers_version": "4.57.1",
65
+ "use_cache": true,
66
+ "use_qk_norm": true,
67
+ "vocab_size": 151552
68
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151329,
6
+ 151336,
7
+ 151338
8
+ ],
9
+ "pad_token_id": 151329,
10
+ "transformers_version": "4.57.1"
11
+ }
model-00001-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8287212920f10acb0a8e8cb9a945e072aee2b805a0bb0cc5e0af3b4ab8ff1930
3
+ size 4292487492
model-00003-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bcfcde4517dfd30963258b75d931bf84556240d1e0ad401aee2a4baa0090b6
3
+ size 4294924997
model-00004-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a421bf2a43a4cdfa9c00d11b7d1ab8924ba1cdfed4a15c89b8aa442ac0f70a
3
+ size 4291744699
model-00005-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313722634f2d5912d74ebf3ec9e574e45d1d62de6e7d7b1285469f94b0d0d456
3
+ size 4291746062
model-00006-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d12ae1c9e400bba815630d648d3370be5b472a5268e7ecf1ff909875cd1ff536
3
+ size 4291748359
model-00008-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd1f7215ffaedd92737c54ba40dbc4f00424177d96eb63b568875792cee2d30f
3
+ size 4291748451
model-00009-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af1c63662702e2d8dcffffd0b57195ee138db6b76d01c5273dfc6de0d182c52
3
+ size 4291748451
model-00010-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b13c8694893120498919eb992ab9946bb51030d5568e801bb7da00467d05bf0
3
+ size 4291748451
model-00011-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940d803f2fcaff826c4475bde87f210f45db4c6a6dedb8b801c83243dbe47c82
3
+ size 4271018395
model-00012-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2ef4f873dff091cf4054350df480b177b5cac913504d2f1949dfeed950d01f
3
+ size 4292849850
model-00013-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ce58eb47eb8d99b6aa6806d56f6143c3a76cd1b11d4d6948adcba2eedd947d
3
+ size 4291748313
model-00014-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7834257872074069f847ad327068131d684431bef7c2634c0f4a16e54a0924a
3
+ size 4291748313
model-00015-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55fc9733bf4cbb775246b86c9a9cebc7c68a2d2f7dcf57204c565e0ffde60f1a
3
+ size 4291748535
model-00016-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed93ea764ca6f253572a5bad9ae164cbba06dce4a04e62e2542350f15cd2cfb
3
+ size 4291748451
model-00017-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087e02667e513e682fa092261be346a88e2c7bcff2bc10206925e268df7af0de
3
+ size 4291748451
model-00019-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8f20876c83534785b98342e711a4006b03ef855a96c133b72e487c81d53c9f
3
+ size 4291748553
model-00020-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e86b7b8844b8aa49cb7444cd46df7d3d843f4da2b25c11c34b32eadb2d44e625
3
+ size 4294928529
model-00021-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a045415f861208d94221949275c0355d14ab52609f1d4924cc0a6f18de091fc
3
+ size 4291748313
model-00022-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d6d1d1209e40051808688499f5805d7c2936307f27e37e6f591b39552394ad
3
+ size 4291748313
model-00023-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39f35db812f66d4dfde6b51f9a700d7d6cf08b0e407c0b9151140415b2ec656
3
+ size 4291748451
model-00024-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b73e701a9aa62b59fc4d861280baf8136d23c1886729b7f84ae0b3f735709c
3
+ size 4291748455
model-00026-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc6a8aeea8d5dceefd16cd09fa2c7ae11de093f6f9af386fe31e605a4fc68eb
3
+ size 4291748451
model-00028-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87afc9449a7d8c8caaeabbb2b8303a506e541816b29aacc77dae1b09ca09505
3
+ size 4294928697
model-00029-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:791a82daf89e91e7d37c5605266be77159455e8b042197bf6df77c9a6dc6980d
3
+ size 4291748347
model-00030-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9e322021c5e024a964c9e070b50440ef02e30cfc695874959d56c5747e0109
3
+ size 4291748313
model-00031-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1d860450fd1d9b0f80a74f6c304c52d2747f9e7fa1accf509f1ac94fc0267d
3
+ size 4291748367
model-00032-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9876950c42adcb8818414c37e797bceacdc1c2381ae1dee09f5647753825f5da
3
+ size 4291748553
model-00033-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0082b1a75892cac5da1a0793643907916813fed5231ae1153353a992ef6765c6
3
+ size 4291748451
model-00034-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ecbee4c3367c9635b9e157c224c41104e49f8dbf73ad16b0c9a034b47d6a6c
3
+ size 4291748451
model-00035-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1baef801eaf2dcb3a9b24c46a5aa0038dee3e274da1473a0211b5b0525c3d2a7
3
+ size 4291748451
model-00037-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384dfe432a27c9a46372b9367b07d060c4639dbe5e14e69c9b262104e40827f2
3
+ size 4292849850
model-00038-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa18fdf2cc5fb65de4d5b1dac20568dad6556a29ef65c11cbf1a309566322a41
3
+ size 4291748313
model-00039-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca0528d391df89d134b17c5d3ac5ec32fac86997e2ac01a32e8cf8acf87efd8
3
+ size 4291748313
model-00040-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478c2c29cdf69e1802dcb8e38a9376627c061d2f302bfa59b938b5f13aeddd80
3
+ size 4291748535
model-00041-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f756e031a0c7d6f6f6f464eb9517ca4282bf02bc0f1c87e0bacd85595b500b75
3
+ size 4291748451
model-00042-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e512ea22544a392cf50d3e1a505110645fe229033d4bb7818802ef431423c02
3
+ size 4291748451
model-00044-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315bf2b8c39fadbde4767bc5827bab9084f4e40504b26d027d79c4ef0a9ed0ea
3
+ size 4291748553
model-00045-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0b44e823557c614ff91a309d4f29a7b2b71b3448c5a8fb3e1ce7e064400587
3
+ size 4294928529
model-00046-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afefa3b6f7c78c1605cfce41a7ee9a7c97f4bbb48cf07a372c337cddc5c5f150
3
+ size 4291748313
model-00047-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6464538bf8e29e5bdb821ddf1a4d1772e80047e6477e79157d70d190add05f
3
+ size 4291748313
model-00049-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5286a5048185454c4379075210e7d7666ce81154eadc88564249592ad115da6b
3
+ size 994162111
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63cb2651471c776ee995eac6c02552d8b8c6292221628ae79db479b8891fa857
3
+ size 15770277
quant_log.csv ADDED
The diff for this file is too large to render. See raw diff
 
quantize_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 32,
4
+ "desc_act": false,
5
+ "sym": true,
6
+ "lm_head": false,
7
+ "quant_method": "gptq",
8
+ "checkpoint_format": "gptq",
9
+ "pack_dtype": "int32",
10
+ "meta": {
11
+ "quantizer": [
12
+ "gptqmodel:5.0.0-dev0"
13
+ ],
14
+ "uri": "https://github.com/modelcloud/gptqmodel",
15
+ "damp_percent": 0.05,
16
+ "damp_auto_increment": 0.01,
17
+ "static_groups": false,
18
+ "true_sequential": true,
19
+ "mse": 0.0,
20
+ "v2": false,
21
+ "v2_alpha": 0.25,
22
+ "act_group_aware": true
23
+ },
24
+ "pack_impl": "cpu"
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>",
17
+ "<|begin_of_audio|>",
18
+ "<|end_of_audio|>",
19
+ "<|begin_of_transcription|>",
20
+ "<|end_of_transcription|>",
21
+ "<|code_prefix|>",
22
+ "<|code_middle|>",
23
+ "<|code_suffix|>",
24
+ "/nothink"
25
+ ],
26
+ "eos_token": {
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": "<|endoftext|>"
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
3
+ size 19970700