Hugging Face's logo

OwenArli
/
test-quant

Safetensors
glm4_moe
4-bit precision
gptq_marlin
Model card Files
xet
Community
OwenArli commited on
Commit
9d7d30b
·
verified ·
1 Parent(s): 87dd766

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 +86 -0
  3. config.json +79 -0
  4. generation_config.json +11 -0
  5. model-00001-of-00058.safetensors +3 -0
  6. model-00002-of-00058.safetensors +3 -0
  7. model-00003-of-00058.safetensors +3 -0
  8. model-00004-of-00058.safetensors +3 -0
  9. model-00005-of-00058.safetensors +3 -0
  10. model-00006-of-00058.safetensors +3 -0
  11. model-00007-of-00058.safetensors +3 -0
  12. model-00009-of-00058.safetensors +3 -0
  13. model-00010-of-00058.safetensors +3 -0
  14. model-00013-of-00058.safetensors +3 -0
  15. model-00014-of-00058.safetensors +3 -0
  16. model-00015-of-00058.safetensors +3 -0
  17. model-00016-of-00058.safetensors +3 -0
  18. model-00017-of-00058.safetensors +3 -0
  19. model-00018-of-00058.safetensors +3 -0
  20. model-00019-of-00058.safetensors +3 -0
  21. model-00020-of-00058.safetensors +3 -0
  22. model-00021-of-00058.safetensors +3 -0
  23. model-00022-of-00058.safetensors +3 -0
  24. model-00023-of-00058.safetensors +3 -0
  25. model-00024-of-00058.safetensors +3 -0
  26. model-00025-of-00058.safetensors +3 -0
  27. model-00026-of-00058.safetensors +3 -0
  28. model-00027-of-00058.safetensors +3 -0
  29. model-00028-of-00058.safetensors +3 -0
  30. model-00029-of-00058.safetensors +3 -0
  31. model-00030-of-00058.safetensors +3 -0
  32. model-00033-of-00058.safetensors +3 -0
  33. model-00034-of-00058.safetensors +3 -0
  34. model-00035-of-00058.safetensors +3 -0
  35. model-00036-of-00058.safetensors +3 -0
  36. model-00038-of-00058.safetensors +3 -0
  37. model-00040-of-00058.safetensors +3 -0
  38. model-00042-of-00058.safetensors +3 -0
  39. model-00043-of-00058.safetensors +3 -0
  40. model-00047-of-00058.safetensors +3 -0
  41. model-00048-of-00058.safetensors +3 -0
  42. model-00054-of-00058.safetensors +3 -0
  43. model-00055-of-00058.safetensors +3 -0
  44. model-00056-of-00058.safetensors +3 -0
  45. model-00058-of-00058.safetensors +3 -0
  46. model.safetensors.index.json +3 -0
  47. quant_log.csv +0 -0
  48. quantize_config.json +36 -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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
17
+ {%- macro visible_text(content) -%}
18
+ {%- if content is string -%}
19
+ {{- content }}
20
+ {%- elif content is iterable and content is not mapping -%}
21
+ {%- for item in content -%}
22
+ {%- if item is mapping and item.type == 'text' -%}
23
+ {{- item.text }}
24
+ {%- elif item is string -%}
25
+ {{- item }}
26
+ {%- endif -%}
27
+ {%- endfor -%}
28
+ {%- else -%}
29
+ {{- content }}
30
+ {%- endif -%}
31
+ {%- endmacro -%}
32
+ {%- set ns = namespace(last_user_index=-1) %}
33
+ {%- for m in messages %}
34
+ {%- if m.role == 'user' %}
35
+ {% set ns.last_user_index = loop.index0 -%}
36
+ {%- endif %}
37
+ {%- endfor %}
38
+ {% for m in messages %}
39
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
40
+ {%- elif m.role == 'assistant' -%}
41
+ <|assistant|>
42
+ {%- set reasoning_content = '' %}
43
+ {%- set content = visible_text(m.content) %}
44
+ {%- if m.reasoning_content is string %}
45
+ {%- set reasoning_content = m.reasoning_content %}
46
+ {%- else %}
47
+ {%- if '</think>' in content %}
48
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
49
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
53
+ {{ '<think>' + reasoning_content.strip() + '</think>'}}
54
+ {%- else -%}
55
+ {{ '</think>' }}
56
+ {%- endif -%}
57
+ {%- if content.strip() -%}
58
+ {{ content.strip() }}
59
+ {%- endif -%}
60
+ {% if m.tool_calls %}
61
+ {% for tc in m.tool_calls %}
62
+ {%- if tc.function %}
63
+ {%- set tc = tc.function %}
64
+ {%- endif %}
65
+ {{- '<tool_call>' + tc.name -}}
66
+ {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
67
+ {% endif %}
68
+ {%- elif m.role == 'tool' -%}
69
+ {%- if m.content is string -%}
70
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
71
+ {{- '<|observation|>' }}
72
+ {%- endif %}
73
+ {{- '<tool_response>' }}
74
+ {{- m.content }}
75
+ {{- '</tool_response>' }}
76
+ {%- else -%}
77
+ <|observation|>{% for tr in m.content %}
78
+ <tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
79
+ {% endif -%}
80
+ {%- elif m.role == 'system' -%}
81
+ <|system|>{{ visible_text(m.content) }}
82
+ {%- endif -%}
83
+ {%- endfor -%}
84
+ {%- if add_generation_prompt -%}
85
+ <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
86
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dynamic": {
38
+ "+:model[.]layers[.]([0-9]|1[0-1]|8[0-9]|9[0-2])[.].*": {
39
+ "bits": 8
40
+ },
41
+ "-:.*embed_tokens.*": {},
42
+ "-:.*lm_head.*": {},
43
+ "-:.*shared_experts.*": {},
44
+ "-:.*shared_head.*": {},
45
+ "-:model[.]layers[.].*[.]self_attn[.].*": {}
46
+ },
47
+ "format": "gptq",
48
+ "group_size": 128,
49
+ "lm_head": false,
50
+ "meta": {
51
+ "act_group_aware": true,
52
+ "damp_auto_increment": 0.01,
53
+ "damp_percent": 0.05,
54
+ "gptaq": false,
55
+ "gptaq_alpha": 0.25,
56
+ "mse": 0.0,
57
+ "quantizer": [
58
+ "gptqmodel:5.4.4"
59
+ ],
60
+ "static_groups": false,
61
+ "true_sequential": true,
62
+ "uri": "https://github.com/modelcloud/gptqmodel"
63
+ },
64
+ "pack_dtype": "int32",
65
+ "pack_impl": "cpu",
66
+ "quant_method": "gptq_marlin",
67
+ "sym": true
68
+ },
69
+ "rms_norm_eps": 1e-05,
70
+ "rope_scaling": null,
71
+ "rope_theta": 1000000,
72
+ "routed_scaling_factor": 2.5,
73
+ "tie_word_embeddings": false,
74
+ "topk_group": 1,
75
+ "transformers_version": "4.57.3",
76
+ "use_cache": true,
77
+ "use_qk_norm": true,
78
+ "vocab_size": 151552
79
+ }
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": "4.57.3"
11
+ }
model-00001-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e7142b5d5c40bd97c43ba9103635d82fe2f3d6d2d5e394faf3bc28419da1df
3
+ size 4283218117
model-00002-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab55fd442812ba7c681d7a59079db1c2c4c3c21aa6f893a4d65f5f8258d17724
3
+ size 4195320972
model-00003-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46460ba8acf6be574b0667f57af8c689b6f10369023e96deaef9573cf2f845a7
3
+ size 4179571519
model-00004-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc72181c5443d15491cd278161e0a90f9ee70d80c27b76454c4c12fda78a7ba
3
+ size 4179571519
model-00005-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd2fe92538f67f6888d9ea088221902e9028e547ebf24bc5c129d9418d4a385
3
+ size 4179571519
model-00006-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6421b2b84e059644787c46d43e426e9662da2af90424883f9d020ebe0e3540f9
3
+ size 4179571519
model-00007-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ea63470ed123299778300134484e57f044790ecfa91eef37bcd5f609c213fe
3
+ size 4179571519
model-00009-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c77096ac4179b0023cafe842a020afb945e601718ae28d4617b3b43f973d038
3
+ size 4290491798
model-00010-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29be3d74ef7735e6caa7acf885d9aaee8e855a7bb15c154a51ecfa4a846322b
3
+ size 4290491794
model-00013-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e101420569e1c86ff32572d65232db51a99c02182bb3ebb0850692f08d05fe6c
3
+ size 4290491908
model-00014-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfa65b7c6bde2c6e4a56827a328e67b5a9741ed1cddf855f4d7fed99640d3cc
3
+ size 4290477666
model-00015-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f36f53ec6070d6d10900f1a85cb3568b78894e444e36ac680eca386bc20796
3
+ size 4290493734
model-00016-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a53d420ad41e86cf5ca9c6b78abede191e23e064f213372210a12dfc0d46628f
3
+ size 4295148270
model-00017-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9826444b7b74d486c9b8bb11147296f014a6e7fcea3233086c182448924e6eee
3
+ size 4294739724
model-00018-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:000741bc1ef5d94667b3cdddd8f3b0690951f4f91250566f3b482cdf5cdc249e
3
+ size 4294739806
model-00019-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b42a34112c25f7214f957c46d8d33ca5ba1f7a4b20bb8b3b5bf795a888001d6
3
+ size 4294739806
model-00020-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1cfd8d2208094839f1f9c2c1a431f82e559c82e3f5826cb0f4f11a59785e6c4
3
+ size 4294740034
model-00021-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0238121ac4b4aab7001092a71e8a3ada12ad82718a3a994182c09a009fcc4a1
3
+ size 4294740152
model-00022-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c2db864c32d8f6100b1ed12803ff75296c0896bae2c4f980bbb7723a066503
3
+ size 4294740586
model-00023-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61945d87ccf30d417186bbd6f12c278ba8ecc9030ac5340aa54b8178f8df1328
3
+ size 4294739806
model-00024-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7807c0af2e19b1e461242a120d54bc8dbea627ab2b702ad8f583c7c677be371
3
+ size 4294739806
model-00025-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14bf7deedd58bf1eb10e09a850c15f5c5fc7ba45b2fc3687179a0c62fa73515
3
+ size 4294739856
model-00026-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41e5db1b39abd1cca4a693a4619e6d88d31a01ca07b0f5f6564342a748563fa
3
+ size 4294740152
model-00027-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a9853fd1beb811b975f5fbcf2cbef05d15aade9ae66c885bc468d46090ad6e
3
+ size 4294740860
model-00028-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbf1660f5610e64b0c61d73ee5682bfec319d4028736c9f745a4e93f1ff2c30
3
+ size 4294739712
model-00029-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f3210c8e41c4d833d16f6150fe23c8d4a35d2b66661142c92262d38dbdaaa7
3
+ size 4294739806
model-00030-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e80dee382d839d9b6f85f40e2f20e4b3281cf3cee685aacad9166c6dbf31d5
3
+ size 4294739806
model-00033-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ae10791e0d35c630b6ee057157cbba745f4faac546e81d8be40820fe0a92a4
3
+ size 4294740598
model-00034-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b939407b4bcc2cfc0b03ae6cf662b9ff5ebab932171ab51f7e5be6961af806
3
+ size 4294739806
model-00035-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8ebb80845cbd6439be87013d7c30c7c3367ae6af22a77cf6026a58430f4cb5
3
+ size 4294739806
model-00036-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f381df7b21ac43a60848f63ea636f2bb6aa5e55aecda198d91ea4ad0af2b19b
3
+ size 4294739844
model-00038-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba3fb8a3cddb7858d5a69e3013418520bc3e78211fdfebfea54ab249335d396
3
+ size 4294740884
model-00040-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f662e04ad187ff80fad7851388c3de52db301fa2a5eb3a485f69d54106b5e8d
3
+ size 4294739806
model-00042-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e571d49a14a1d3dea660082982b10d7408518ff1d1c8307ef9f0e60935da5c80
3
+ size 4294740010
model-00043-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8208e6cfa74780cdabee5db68de39f67a8075989f6c1a6f226f93796c8a26d70
3
+ size 4294740152
model-00047-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6842edfeaf2261ac6787c21e0f71c6a2702a1fab083ce0a19e9b05c87fa0c0b
3
+ size 4294739832
model-00048-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f9cebf4b51e83093c9b4284277a17f6e7a5edefaf7709a7ac2bcc2f84c3547
3
+ size 4294522883
model-00054-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb45809fa2cb515c8d6be7b8272d39ff72cc38ed1b05bf44664448dba33436d9
3
+ size 4290493927
model-00055-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be4a35cb08def4b69b30b2db69e01fe140424e12340540241b9c3fd79114664
3
+ size 4290494037
model-00056-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db608d433fc46e712d5eb8bd42c03d97c61e48afcf73a9fee5fe1729591002d
3
+ size 4290479795
model-00058-of-00058.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09f45b91bc0b9a1f2baa2fe929792f3f9144e668c32be86fb04d195e74e3a24a
3
+ size 4258087401
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec68bdb420321d430e98de538c787bc9a80143bfca0d70b0812937d50c1aa12e
3
+ size 15640070
quant_log.csv ADDED
The diff for this file is too large to render. See raw diff
 
quantize_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "dynamic": {
4
+ "-:.*embed_tokens.*": {},
5
+ "-:.*shared_head.*": {},
6
+ "-:.*shared_experts.*": {},
7
+ "-:.*lm_head.*": {},
8
+ "-:model[.]layers[.].*[.]self_attn[.].*": {},
9
+ "+:model[.]layers[.]([0-9]|1[0-1]|8[0-9]|9[0-2])[.].*": {
10
+ "bits": 8
11
+ }
12
+ },
13
+ "group_size": 128,
14
+ "desc_act": false,
15
+ "sym": true,
16
+ "lm_head": false,
17
+ "quant_method": "gptq",
18
+ "checkpoint_format": "gptq",
19
+ "pack_dtype": "int32",
20
+ "meta": {
21
+ "quantizer": [
22
+ "gptqmodel:5.4.4"
23
+ ],
24
+ "uri": "https://github.com/modelcloud/gptqmodel",
25
+ "damp_percent": 0.05,
26
+ "damp_auto_increment": 0.01,
27
+ "static_groups": false,
28
+ "true_sequential": true,
29
+ "mse": 0.0,
30
+ "gptaq": false,
31
+ "gptaq_alpha": 0.25,
32
+ "act_group_aware": true
33
+ },
34
+ "pack_impl": "cpu",
35
+ "format": "gptq"
36
+ }
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