alpindale commited on
Commit
5219edf
·
verified ·
1 Parent(s): a139639

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 +1 -0
  2. chat_template.jinja +103 -0
  3. config.json +89 -0
  4. generation_config.json +10 -0
  5. model-00003-of-00072.safetensors +3 -0
  6. model-00006-of-00072.safetensors +3 -0
  7. model-00007-of-00072.safetensors +3 -0
  8. model-00011-of-00072.safetensors +3 -0
  9. model-00013-of-00072.safetensors +3 -0
  10. model-00014-of-00072.safetensors +3 -0
  11. model-00015-of-00072.safetensors +3 -0
  12. model-00017-of-00072.safetensors +3 -0
  13. model-00018-of-00072.safetensors +3 -0
  14. model-00020-of-00072.safetensors +3 -0
  15. model-00021-of-00072.safetensors +3 -0
  16. model-00027-of-00072.safetensors +3 -0
  17. model-00028-of-00072.safetensors +3 -0
  18. model-00031-of-00072.safetensors +3 -0
  19. model-00034-of-00072.safetensors +3 -0
  20. model-00036-of-00072.safetensors +3 -0
  21. model-00037-of-00072.safetensors +3 -0
  22. model-00039-of-00072.safetensors +3 -0
  23. model-00041-of-00072.safetensors +3 -0
  24. model-00043-of-00072.safetensors +3 -0
  25. model-00044-of-00072.safetensors +3 -0
  26. model-00046-of-00072.safetensors +3 -0
  27. model-00047-of-00072.safetensors +3 -0
  28. model-00048-of-00072.safetensors +3 -0
  29. model-00049-of-00072.safetensors +3 -0
  30. model-00050-of-00072.safetensors +3 -0
  31. model-00051-of-00072.safetensors +3 -0
  32. model-00052-of-00072.safetensors +3 -0
  33. model-00053-of-00072.safetensors +3 -0
  34. model-00054-of-00072.safetensors +3 -0
  35. model-00055-of-00072.safetensors +3 -0
  36. model-00057-of-00072.safetensors +3 -0
  37. model-00058-of-00072.safetensors +3 -0
  38. model-00060-of-00072.safetensors +3 -0
  39. model-00062-of-00072.safetensors +3 -0
  40. model-00063-of-00072.safetensors +3 -0
  41. model-00064-of-00072.safetensors +3 -0
  42. model-00066-of-00072.safetensors +3 -0
  43. model-00067-of-00072.safetensors +3 -0
  44. model-00068-of-00072.safetensors +3 -0
  45. model-00071-of-00072.safetensors +3 -0
  46. model-00072-of-00072.safetensors +3 -0
  47. model.safetensors.index.json +0 -0
  48. recipe.yaml +20 -0
  49. special_tokens_map.json +40 -0
  50. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ 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 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "config_groups": {
35
+ "group_0": {
36
+ "format": "int-quantized",
37
+ "input_activations": {
38
+ "actorder": null,
39
+ "block_structure": null,
40
+ "dynamic": true,
41
+ "group_size": null,
42
+ "num_bits": 8,
43
+ "observer": null,
44
+ "observer_kwargs": {},
45
+ "strategy": "token",
46
+ "symmetric": true,
47
+ "type": "int"
48
+ },
49
+ "output_activations": null,
50
+ "targets": [
51
+ "Linear"
52
+ ],
53
+ "weights": {
54
+ "actorder": null,
55
+ "block_structure": null,
56
+ "dynamic": false,
57
+ "group_size": null,
58
+ "num_bits": 8,
59
+ "observer": "minmax",
60
+ "observer_kwargs": {},
61
+ "strategy": "channel",
62
+ "symmetric": true,
63
+ "type": "int"
64
+ }
65
+ }
66
+ },
67
+ "format": "int-quantized",
68
+ "global_compression_ratio": null,
69
+ "ignore": [
70
+ "lm_head"
71
+ ],
72
+ "kv_cache_scheme": null,
73
+ "quant_method": "compressed-tensors",
74
+ "quantization_status": "compressed",
75
+ "sparsity_config": {},
76
+ "transform_config": {},
77
+ "version": "0.11.1.a20250929"
78
+ },
79
+ "rms_norm_eps": 1e-05,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "routed_scaling_factor": 2.5,
83
+ "tie_word_embeddings": false,
84
+ "topk_group": 1,
85
+ "transformers_version": "4.56.2",
86
+ "use_cache": true,
87
+ "use_qk_norm": true,
88
+ "vocab_size": 151552
89
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151329,
5
+ 151336,
6
+ 151338
7
+ ],
8
+ "pad_token_id": 151329,
9
+ "transformers_version": "4.56.2"
10
+ }
model-00003-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac77ad4bb789058b2578f94871bcbca84b62908ecc65b202099d6ad9001936cc
3
+ size 4998103744
model-00006-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad40f9336c7ecb066810cfa34641f316bc2b535877d9f992c0f7a0abd9015414
3
+ size 4993852200
model-00007-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8763e8e8b905c6a3baf0e4142be77a4039013468f2b5928b3f079f40c9f506ca
3
+ size 4998104608
model-00011-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059e9bdbf72e2a7f03607448ebe35b206eca1cd73e54c0fb6ad1bcf52fe992d1
3
+ size 4993853064
model-00013-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2575e328cc8edf57a9c96c3175f858f838484350a28f81dee721489e21d140bf
3
+ size 4993846160
model-00014-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d00237637fba0cb985f12fb3d2479a0a515d4c3f3366c46c465b73fb729f2f3
3
+ size 4998104984
model-00015-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de97771d00a1d5187a7564bc34f776b8d81e5cd5e8aa1294f968e267ed81d1c7
3
+ size 4993853120
model-00017-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8be494937d1b7a45789fd6b92906fa1b2efbd4be3115dcbe7e2f01bf0aedd5
3
+ size 4993846232
model-00018-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ab858c30ba48d4e25fa40a114c6c44108a0b31aa26baa747222a8dd18f4cef
3
+ size 4998104984
model-00020-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2c949ed4df0c07022ec6ee3bfdb2e67490741fae398a908240f71d456dbd4e
3
+ size 4993853200
model-00021-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d247773dffb9052d2a2ff239336819dd33a022d631462db460d98b6a4a2b6a7c
3
+ size 4993846304
model-00027-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37a8599466d884c636d2a2e63de4e31f80ca5c0fcffc66f603fe037c5ed4a57
3
+ size 4993853120
model-00028-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c372029a04f2d1ce515a6ace38cfe4becf32cb539f56fc35f41545287f3bbb
3
+ size 4993853344
model-00031-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc1291ec759820ed6f8dd2be7c65b07573ac793f91f1eedb5a82723bd1c7531
3
+ size 4993853152
model-00034-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58eae74fbc4fdaffae3508e56e2d0d039ec92385c0c30e3a17af7aab027b76fa
3
+ size 4993845952
model-00036-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a40a87bca7d66b374eab36eacff7954633e9f6d60b68356765b879c4771f9a
3
+ size 4971903376
model-00037-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2e1de00e01f1139f2beaea204e60fa678120f6eeb66ede1370195089d3c11c
3
+ size 4996444640
model-00039-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28644c0d3aee8444009bdf422bbef87c8966149e5b4d7c658fac9d7a4030512a
3
+ size 4993853288
model-00041-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39fdefdb8570714bd148da5fd2ab152ff199e10a2673608e35b379fb9c38d217
3
+ size 4993853096
model-00043-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7b7f333a50b479e3e653a46a6282ea814e08b3d0cbbefca2782bb5dd62d46b
3
+ size 4993853360
model-00044-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cac993c1f4ea8480222b657fc39abfd51530e25ffee4a4b83536ae63a51505e
3
+ size 4998104984
model-00046-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e027a656aeb6ef5d915abd4235b55d1a515922018fe3db5fac559a563028c701
3
+ size 4993845992
model-00047-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d56513358c95e4e94821781d9722d6fce13b1d39731402095a6974c9c3dd9c4
3
+ size 4993853432
model-00048-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30022cf760a17f5e4922849f3137ad79258ed1cdad4f068de6e40805d098785
3
+ size 4998104984
model-00049-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8bd434dabf51e507a84024d06f6316c9f2e3d1efaa1c6cffea3d5be7c78868
3
+ size 4993853120
model-00050-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c191de47ed157d5efea81c19d8fcdfa136a6d39e114ee2063ba0d9b0f2516d5
3
+ size 4993846064
model-00051-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7d7259ddb27c4c628803ca282724bed1ec09522a89f0b25be6bf17c3f9a460
3
+ size 4990274256
model-00052-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6bfb763a822457de13afcf5d251ceb26a0f2375ea0b2cec487849cfab20e30
3
+ size 4993816208
model-00053-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4664942f63681cde9a3a4461460fe228ab60993706c106902941343ea6dba1
3
+ size 4993845952
model-00054-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b62456ca975de0331c5ab79b71a95287e4e7633034c64af72bc41dcec865fc
3
+ size 4993853312
model-00055-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325707ea5841566aaf7cf207c1422a65675801656a04c207384b3a351d09e0ac
3
+ size 4998104984
model-00057-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3dda22d0aede442d305677f42897cf2d78dcfc65ed7cd56caec9b425eb8c7f
3
+ size 4993845952
model-00058-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3c72b2912db7384586c6e779ac97f58e9aba52e585251e138cd3809272722e
3
+ size 4993853384
model-00060-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0908615b54ec1031ca76333a38395692479e9cfed4d924383c3190c422673e99
3
+ size 4993853120
model-00062-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c0a6d09da6725db8861f67808474e753d711a5e1a42a601ad28fca551d30d7
3
+ size 4993853456
model-00063-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8de54c1d09ab4fe877fd4c259c7085972cd37bcc9e4a751b5a543abb0af34b8
3
+ size 4998104984
model-00064-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1969d70e431bf35f574c80b158a5d67b2d406fa5fc834cdfa16ff6064a71de3a
3
+ size 4993853120
model-00066-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e3e39f54f6db83b9cc919f3bb8e7838bc3b40c254520bc63ced74067ee510e
3
+ size 4998105040
model-00067-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ef205906956a99d6a5b9e884037f7bfda8569450aafbdd44832005cd64ba93
3
+ size 4993853064
model-00068-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20d53ae55e4842cdaa2732d4f699a06edc2f3f1da0fc9ecbcb2d2fe83edb42a
3
+ size 4993853120
model-00071-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff2c69ec7b19d530ed6274f5a663018d4897f63397c840a51e1cd306a88d1cd
3
+ size 3503836824
model-00072-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ed732a1f52d39814adc6a0b127bad1c816b89d7055fa07b029cba98deba7bf
3
+ size 1551892608
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ SmoothQuantModifier:
4
+ smoothing_strength: 0.8
5
+ mappings:
6
+ - !!python/tuple
7
+ - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
8
+ - re:.*input_layernorm
9
+ - !!python/tuple
10
+ - ['re:.*gate_proj', 're:.*up_proj']
11
+ - re:.*post_attention_layernorm
12
+ ignore: []
13
+ GPTQModifier:
14
+ targets: [Linear]
15
+ ignore: [lm_head, 're:.*mlp.gate$']
16
+ scheme: W8A8
17
+ block_size: 128
18
+ dampening_frac: 0.01
19
+ actorder: static
20
+ offload_hessians: false
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
3
+ size 19970700