Hugging Face's logo

baseten-admin
/
glm-4.6-fp4-mlp

Safetensors
glm4_moe
8-bit precision
modelopt
Model card Files
xet
Community
baseten-admin commited on
Commit
e0431f7
·
verified ·
1 Parent(s): db39084

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 +165 -0
  4. generation_config.json +10 -0
  5. hf_quant_config.json +106 -0
  6. model-00001-of-00044.safetensors +3 -0
  7. model-00002-of-00044.safetensors +3 -0
  8. model-00003-of-00044.safetensors +3 -0
  9. model-00004-of-00044.safetensors +3 -0
  10. model-00005-of-00044.safetensors +3 -0
  11. model-00006-of-00044.safetensors +3 -0
  12. model-00007-of-00044.safetensors +3 -0
  13. model-00008-of-00044.safetensors +3 -0
  14. model-00009-of-00044.safetensors +3 -0
  15. model-00010-of-00044.safetensors +3 -0
  16. model-00011-of-00044.safetensors +3 -0
  17. model-00012-of-00044.safetensors +3 -0
  18. model-00013-of-00044.safetensors +3 -0
  19. model-00014-of-00044.safetensors +3 -0
  20. model-00015-of-00044.safetensors +3 -0
  21. model-00016-of-00044.safetensors +3 -0
  22. model-00017-of-00044.safetensors +3 -0
  23. model-00018-of-00044.safetensors +3 -0
  24. model-00019-of-00044.safetensors +3 -0
  25. model-00020-of-00044.safetensors +3 -0
  26. model-00021-of-00044.safetensors +3 -0
  27. model-00022-of-00044.safetensors +3 -0
  28. model-00023-of-00044.safetensors +3 -0
  29. model-00024-of-00044.safetensors +3 -0
  30. model-00025-of-00044.safetensors +3 -0
  31. model-00026-of-00044.safetensors +3 -0
  32. model-00027-of-00044.safetensors +3 -0
  33. model-00028-of-00044.safetensors +3 -0
  34. model-00029-of-00044.safetensors +3 -0
  35. model-00030-of-00044.safetensors +3 -0
  36. model-00031-of-00044.safetensors +3 -0
  37. model-00032-of-00044.safetensors +3 -0
  38. model-00033-of-00044.safetensors +3 -0
  39. model-00034-of-00044.safetensors +3 -0
  40. model-00035-of-00044.safetensors +3 -0
  41. model-00036-of-00044.safetensors +3 -0
  42. model-00037-of-00044.safetensors +3 -0
  43. model-00038-of-00044.safetensors +3 -0
  44. model-00039-of-00044.safetensors +3 -0
  45. model-00041-of-00044.safetensors +3 -0
  46. model-00042-of-00044.safetensors +3 -0
  47. model-00044-of-00044.safetensors +3 -0
  48. model.safetensors.index.json +3 -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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ model.safetensors.index.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 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 1000000,
36
+ "routed_scaling_factor": 2.5,
37
+ "tie_word_embeddings": false,
38
+ "topk_group": 1,
39
+ "transformers_version": "4.57.0",
40
+ "use_cache": true,
41
+ "use_qk_norm": true,
42
+ "vocab_size": 151552,
43
+ "quantization_config": {
44
+ "config_groups": {
45
+ "group_0": {
46
+ "input_activations": {
47
+ "dynamic": false,
48
+ "num_bits": 4,
49
+ "type": "float",
50
+ "group_size": 16
51
+ },
52
+ "weights": {
53
+ "dynamic": false,
54
+ "num_bits": 4,
55
+ "type": "float",
56
+ "group_size": 16
57
+ },
58
+ "targets": [
59
+ "Linear"
60
+ ]
61
+ }
62
+ },
63
+ "ignore": [
64
+ "model.layers.0.self_attn*",
65
+ "model.layers.1.self_attn*",
66
+ "model.layers.10.self_attn*",
67
+ "model.layers.11.self_attn*",
68
+ "model.layers.12.self_attn*",
69
+ "model.layers.13.self_attn*",
70
+ "model.layers.14.self_attn*",
71
+ "model.layers.15.self_attn*",
72
+ "model.layers.16.self_attn*",
73
+ "model.layers.17.self_attn*",
74
+ "model.layers.18.self_attn*",
75
+ "model.layers.19.self_attn*",
76
+ "model.layers.2.self_attn*",
77
+ "model.layers.20.self_attn*",
78
+ "model.layers.21.self_attn*",
79
+ "model.layers.22.self_attn*",
80
+ "model.layers.23.self_attn*",
81
+ "model.layers.24.self_attn*",
82
+ "model.layers.25.self_attn*",
83
+ "model.layers.26.self_attn*",
84
+ "model.layers.27.self_attn*",
85
+ "model.layers.28.self_attn*",
86
+ "model.layers.29.self_attn*",
87
+ "model.layers.3.self_attn*",
88
+ "model.layers.30.self_attn*",
89
+ "model.layers.31.self_attn*",
90
+ "model.layers.32.self_attn*",
91
+ "model.layers.33.self_attn*",
92
+ "model.layers.34.self_attn*",
93
+ "model.layers.35.self_attn*",
94
+ "model.layers.36.self_attn*",
95
+ "model.layers.37.self_attn*",
96
+ "model.layers.38.self_attn*",
97
+ "model.layers.39.self_attn*",
98
+ "model.layers.4.self_attn*",
99
+ "model.layers.40.self_attn*",
100
+ "model.layers.41.self_attn*",
101
+ "model.layers.42.self_attn*",
102
+ "model.layers.43.self_attn*",
103
+ "model.layers.44.self_attn*",
104
+ "model.layers.45.self_attn*",
105
+ "model.layers.46.self_attn*",
106
+ "model.layers.47.self_attn*",
107
+ "model.layers.48.self_attn*",
108
+ "model.layers.49.self_attn*",
109
+ "model.layers.5.self_attn*",
110
+ "model.layers.50.self_attn*",
111
+ "model.layers.51.self_attn*",
112
+ "model.layers.52.self_attn*",
113
+ "model.layers.53.self_attn*",
114
+ "model.layers.54.self_attn*",
115
+ "model.layers.55.self_attn*",
116
+ "model.layers.56.self_attn*",
117
+ "model.layers.57.self_attn*",
118
+ "model.layers.58.self_attn*",
119
+ "model.layers.59.self_attn*",
120
+ "model.layers.6.self_attn*",
121
+ "model.layers.60.self_attn*",
122
+ "model.layers.61.self_attn*",
123
+ "model.layers.62.self_attn*",
124
+ "model.layers.63.self_attn*",
125
+ "model.layers.64.self_attn*",
126
+ "model.layers.65.self_attn*",
127
+ "model.layers.66.self_attn*",
128
+ "model.layers.67.self_attn*",
129
+ "model.layers.68.self_attn*",
130
+ "model.layers.69.self_attn*",
131
+ "model.layers.7.self_attn*",
132
+ "model.layers.70.self_attn*",
133
+ "model.layers.71.self_attn*",
134
+ "model.layers.72.self_attn*",
135
+ "model.layers.73.self_attn*",
136
+ "model.layers.74.self_attn*",
137
+ "model.layers.75.self_attn*",
138
+ "model.layers.76.self_attn*",
139
+ "model.layers.77.self_attn*",
140
+ "model.layers.78.self_attn*",
141
+ "model.layers.79.self_attn*",
142
+ "model.layers.8.self_attn*",
143
+ "model.layers.80.self_attn*",
144
+ "model.layers.81.self_attn*",
145
+ "model.layers.82.self_attn*",
146
+ "model.layers.83.self_attn*",
147
+ "model.layers.84.self_attn*",
148
+ "model.layers.85.self_attn*",
149
+ "model.layers.86.self_attn*",
150
+ "model.layers.87.self_attn*",
151
+ "model.layers.88.self_attn*",
152
+ "model.layers.89.self_attn*",
153
+ "model.layers.9.self_attn*",
154
+ "model.layers.90.self_attn*",
155
+ "model.layers.91.self_attn*",
156
+ "lm_head"
157
+ ],
158
+ "quant_algo": "NVFP4",
159
+ "producer": {
160
+ "name": "modelopt",
161
+ "version": "0.37.0.dev82+g340eb7a75"
162
+ },
163
+ "quant_method": "modelopt"
164
+ }
165
+ }
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": "4.57.0"
10
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.37.0.dev82+g340eb7a75"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": null,
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "model.layers.0.self_attn*",
12
+ "model.layers.1.self_attn*",
13
+ "model.layers.10.self_attn*",
14
+ "model.layers.11.self_attn*",
15
+ "model.layers.12.self_attn*",
16
+ "model.layers.13.self_attn*",
17
+ "model.layers.14.self_attn*",
18
+ "model.layers.15.self_attn*",
19
+ "model.layers.16.self_attn*",
20
+ "model.layers.17.self_attn*",
21
+ "model.layers.18.self_attn*",
22
+ "model.layers.19.self_attn*",
23
+ "model.layers.2.self_attn*",
24
+ "model.layers.20.self_attn*",
25
+ "model.layers.21.self_attn*",
26
+ "model.layers.22.self_attn*",
27
+ "model.layers.23.self_attn*",
28
+ "model.layers.24.self_attn*",
29
+ "model.layers.25.self_attn*",
30
+ "model.layers.26.self_attn*",
31
+ "model.layers.27.self_attn*",
32
+ "model.layers.28.self_attn*",
33
+ "model.layers.29.self_attn*",
34
+ "model.layers.3.self_attn*",
35
+ "model.layers.30.self_attn*",
36
+ "model.layers.31.self_attn*",
37
+ "model.layers.32.self_attn*",
38
+ "model.layers.33.self_attn*",
39
+ "model.layers.34.self_attn*",
40
+ "model.layers.35.self_attn*",
41
+ "model.layers.36.self_attn*",
42
+ "model.layers.37.self_attn*",
43
+ "model.layers.38.self_attn*",
44
+ "model.layers.39.self_attn*",
45
+ "model.layers.4.self_attn*",
46
+ "model.layers.40.self_attn*",
47
+ "model.layers.41.self_attn*",
48
+ "model.layers.42.self_attn*",
49
+ "model.layers.43.self_attn*",
50
+ "model.layers.44.self_attn*",
51
+ "model.layers.45.self_attn*",
52
+ "model.layers.46.self_attn*",
53
+ "model.layers.47.self_attn*",
54
+ "model.layers.48.self_attn*",
55
+ "model.layers.49.self_attn*",
56
+ "model.layers.5.self_attn*",
57
+ "model.layers.50.self_attn*",
58
+ "model.layers.51.self_attn*",
59
+ "model.layers.52.self_attn*",
60
+ "model.layers.53.self_attn*",
61
+ "model.layers.54.self_attn*",
62
+ "model.layers.55.self_attn*",
63
+ "model.layers.56.self_attn*",
64
+ "model.layers.57.self_attn*",
65
+ "model.layers.58.self_attn*",
66
+ "model.layers.59.self_attn*",
67
+ "model.layers.6.self_attn*",
68
+ "model.layers.60.self_attn*",
69
+ "model.layers.61.self_attn*",
70
+ "model.layers.62.self_attn*",
71
+ "model.layers.63.self_attn*",
72
+ "model.layers.64.self_attn*",
73
+ "model.layers.65.self_attn*",
74
+ "model.layers.66.self_attn*",
75
+ "model.layers.67.self_attn*",
76
+ "model.layers.68.self_attn*",
77
+ "model.layers.69.self_attn*",
78
+ "model.layers.7.self_attn*",
79
+ "model.layers.70.self_attn*",
80
+ "model.layers.71.self_attn*",
81
+ "model.layers.72.self_attn*",
82
+ "model.layers.73.self_attn*",
83
+ "model.layers.74.self_attn*",
84
+ "model.layers.75.self_attn*",
85
+ "model.layers.76.self_attn*",
86
+ "model.layers.77.self_attn*",
87
+ "model.layers.78.self_attn*",
88
+ "model.layers.79.self_attn*",
89
+ "model.layers.8.self_attn*",
90
+ "model.layers.80.self_attn*",
91
+ "model.layers.81.self_attn*",
92
+ "model.layers.82.self_attn*",
93
+ "model.layers.83.self_attn*",
94
+ "model.layers.84.self_attn*",
95
+ "model.layers.85.self_attn*",
96
+ "model.layers.86.self_attn*",
97
+ "model.layers.87.self_attn*",
98
+ "model.layers.88.self_attn*",
99
+ "model.layers.89.self_attn*",
100
+ "model.layers.9.self_attn*",
101
+ "model.layers.90.self_attn*",
102
+ "model.layers.91.self_attn*",
103
+ "lm_head"
104
+ ]
105
+ }
106
+ }
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e094604cd1e0d6d4e4c8883a37dbaf56a319a6a6758a6da003eebac6a58890
3
+ size 5000149224
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ba40477fcf48464c1f5433dc8900383cdb308e9741423ba87df066e3db4472
3
+ size 4921860760
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8e451b88edb07ad7c881d52d9c47b207455c5a4f9c2bac581252e98d24cee2
3
+ size 4969207552
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3301849351eca97a15b3722c7d01d401d1f98ad928e43fe6be2b7b5db509d86
3
+ size 4996873224
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e838b977f955918d1724e875898618193b71ac7143e86191d12eee5b83d9ad1
3
+ size 4999347328
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22e1b52c29fe9ce2a3faf6a45371455bbb456dee666ba97411da443ee5f9dad
3
+ size 4999347400
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5271b9c55a9a1842b95f77be185bd65d9bc9ca7e674c67b0eecff8dbd58ecd31
3
+ size 4999347392
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ec38f1406cd4a496ef11f55b26c0e5530d81a9e78cf3e9259bea7011e4e008
3
+ size 4999347400
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b583dd1480e42741f14a35ebaf96e3ab1d3973792418b936587b90a51e2ffee2
3
+ size 4999347400
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc98e194b114d90d19b49781c8bae97d58de472b0cfd52609ea14de52a5ca7d
3
+ size 4999347392
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9289a1c1d85f6c488aea34f1e79a31b8479b764182d638443de318e871e46473
3
+ size 4999347400
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:356af918409bcaeced3c34d0267f7d5e09e182db2680f17317c49c792006c63f
3
+ size 4999347528
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fccc37868f64edcf5edc741dcfee97f33fd2c300cf916c6025ce49f7c4f3b2
3
+ size 4999347552
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b5c2f2232e3f257616a67660f63b0d59a79fdc1ff11bb6793b7e7d791f7c48
3
+ size 4999347624
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760b65d9f692ddab1f92a783e59181a534e9adaac27969c62ce0a5ee91e0e652
3
+ size 4999347784
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3984d0a72d4b3580640eaaf4228034db7786c8054723e94bd71f87800d4fed0f
3
+ size 4965614544
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c40c702b433255318283f34bba4a82ef81bbec836bc63ab9b738b96566e8e72
3
+ size 4969211448
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a815d5120650fe165b1f58020cec34843fa56f78223363bf11d74e2647947ad6
3
+ size 4996877104
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09403246369f606703961ca724e23eb1d9deff36c7726877a031279bb32230b
3
+ size 4999347328
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7b87b583987033ba14732e2ed4705c79ef749854d64540d8cc44d8ddb3ca87
3
+ size 4999347400
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240c7adecf31c543c06ac16b854e29dbd305a8c9f1d1e29dedd810f145159f97
3
+ size 4999347392
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b705208ca1d76aec57f9a9895a9d6b3a7f1dc34d0add78dc07a94a3b7772515
3
+ size 4999347400
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954f770303b8e1d813bb97d1bc5c5778acc5a04b4422a130f354560856b565c0
3
+ size 4999347400
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50555f7a06d6db4a64fd699bd8151d48930a25baef6aa9e280881ae6a6643781
3
+ size 4999347392
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f3b76264d71cebb99451a06ebde2be474e2d8d6331c1e1ee28f5aee754cacb
3
+ size 4999347400
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ac8da7cb95b28e79969bb0972ea37069eeccb4d6689443ee1b9e61ef012e0a
3
+ size 4999347528
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d5ef52f24b2d011364446b567567ddd5d548405194ba41a31fe4fa2691749a
3
+ size 4999347552
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec66331bd564fe6fc93c129c45ff35eeb471f512a739d3c467e0ff19dbd3320
3
+ size 4999347624
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e106cb423e774652395dd74d1a3c0f3532d30f378ef8a5d7a91076b93b5a85
3
+ size 4999347784
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ea6e24854b9e221a952a99705fe2ad4fafca02f9cd6b5029a8c11383384ad0
3
+ size 4965614544
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bb6046588a8f74ee06451f0a777b303cb6413cdd17d4734c501b557b6a98949
3
+ size 4969211448
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2fa004cbb2e0959af1acf59ff25e44687318b88e8484fbebac061f108e4a78
3
+ size 4996877104
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9646878ba9daeacd7a124e42252a799b4c1c0d5dd41908a2f8b4ae47b6ea5eb
3
+ size 4999347328
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67ca849a369c40db489c3467b9c145e0e8bd0231edd132c83144d1f2d398aa6
3
+ size 4999347400
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705b63726c3cd986d97fb2e12659bda1fe269127f44e07dd85f65c4eab2b24a7
3
+ size 4999347392
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a8af8b43a6250e3c727e7d648c503d0dbe94772742b660aec8493f93f59906
3
+ size 4999347400
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09ca95417159da4915f853e0d1f7ee1b7dc73b867be8abd639f8b36a6f85d77
3
+ size 4999347400
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7356422e332cef1d0a6d0061ef75ab175ba6f376da2c44ae8b85a131b94a8940
3
+ size 4999347392
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ede61ccf8fd36bbb85bb04143bc960b52683b94e6055a87a59669699bb96cc
3
+ size 4999347400
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bedeb8b73f75dc13072e3b710824ed95c6c08e1eb642f600238504f0a25c96f
3
+ size 4999347552
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5150ab58cb187406c2e9a9dda09d5a9252fddc1293358293cf9eaa9979c90384
3
+ size 4999347624
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d9ac518ca9410132d53ef4696dcba316cd459209c70e495a09e7eee3d54722
3
+ size 4106327720
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5e3cc83c6dbbb3199ea8b5c90ef82b085cb6487bc4892389c2f32facb29b7b
3
+ size 16495658
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