Hugging Face's logo

syntheticlab
/
GLM-4.6-FP8-Dynamic

Safetensors
glm4_moe
compressed-tensors
Model card Files
xet
 Community
reissbaker commited on
Commit
03f4544
·
verified ·
1 Parent(s): 310c569

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. .ipynb_checkpoints/model.safetensors.index-checkpoint.json +0 -0
  3. chat_template.jinja +103 -0
  4. config.json +89 -0
  5. generation_config.json +10 -0
  6. model-00001-of-00072.safetensors +3 -0
  7. model-00005-of-00072.safetensors +3 -0
  8. model-00006-of-00072.safetensors +3 -0
  9. model-00009-of-00072.safetensors +3 -0
  10. model-00012-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-00019-of-00072.safetensors +3 -0
  15. model-00023-of-00072.safetensors +3 -0
  16. model-00024-of-00072.safetensors +3 -0
  17. model-00025-of-00072.safetensors +3 -0
  18. model-00027-of-00072.safetensors +3 -0
  19. model-00028-of-00072.safetensors +3 -0
  20. model-00029-of-00072.safetensors +3 -0
  21. model-00032-of-00072.safetensors +3 -0
  22. model-00033-of-00072.safetensors +3 -0
  23. model-00037-of-00072.safetensors +3 -0
  24. model-00038-of-00072.safetensors +3 -0
  25. model-00039-of-00072.safetensors +3 -0
  26. model-00040-of-00072.safetensors +3 -0
  27. model-00041-of-00072.safetensors +3 -0
  28. model-00042-of-00072.safetensors +3 -0
  29. model-00043-of-00072.safetensors +3 -0
  30. model-00046-of-00072.safetensors +3 -0
  31. model-00047-of-00072.safetensors +3 -0
  32. model-00048-of-00072.safetensors +3 -0
  33. model-00050-of-00072.safetensors +3 -0
  34. model-00052-of-00072.safetensors +3 -0
  35. model-00053-of-00072.safetensors +3 -0
  36. model-00054-of-00072.safetensors +3 -0
  37. model-00056-of-00072.safetensors +3 -0
  38. model-00058-of-00072.safetensors +3 -0
  39. model-00059-of-00072.safetensors +3 -0
  40. model-00060-of-00072.safetensors +3 -0
  41. model-00062-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 +6 -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
.ipynb_checkpoints/model.safetensors.index-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
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": 93,
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": "float-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": "float"
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": "float"
64
+ }
65
+ }
66
+ },
67
+ "format": "float-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": "0.12.2"
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": "4.57.0",
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": "4.57.0"
10
+ }
model-00001-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25721b828db5edfbbc929be8ad7e920890baaf3ffbf9a7fadf9fbc47b677cbbc
3
+ size 4993429864
model-00005-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d23a8569e612d7e32425666d3e6119bec2e4490a5c1e7fbf46213346058d4f3
3
+ size 4993847864
model-00006-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c769475e0161315befa9be4fb9c5aa60126a0eeaf57a1dd36dd8590fab371e5a
3
+ size 4993855304
model-00009-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74c726a5f1f8ad1f30a984063580e18eace50c0f265ae205dcd5c1175a657d1
3
+ size 4993849192
model-00012-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc2233f5a96aaa91eef34f50afa724f91e76e5f2e526b4933a5d71b4a27c762
3
+ size 4993856224
model-00015-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52266f98495c7e5f9ec51d66ccf5e84069752299102847655b94ad14820752c3
3
+ size 4993856224
model-00017-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa33b6de08e05e91c4a96d19d57c3010c59b72208cb9941685ce27df9ed8c73
3
+ size 4993849336
model-00018-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863eee2ef11043f24ac6ed5bb0d6f9fff20675018ff03acb9875b9ae44e335d0
3
+ size 4998108024
model-00019-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb05642de8fd12329f383ec78dfa75314aa3f64ca2d9c8f366abc39a15ccc8b
3
+ size 4993856224
model-00023-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db37fc8d4eaa7c210a8b74a0a9399a02f83d1413451eace8b19034fdbea0aa3
3
+ size 4993856224
model-00024-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef7e9fdadfae6b70af8410044bb400dc16eede2b72d8a19a764c1dba4a72e5e
3
+ size 4993856376
model-00025-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fe7669e82e648a2f5230ab3fb8b2a9a2ff2f0784e23fdf9d2d4e1384df99b08
3
+ size 4998108056
model-00027-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6355fc0e8d56ba65c1ac5c70ccd501d5c51722d7dd36565bbcfb1959b0331960
3
+ size 4993856224
model-00028-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17538028a610180938cff98ea064597a50aa78392c13222358bad8243c90c49a
3
+ size 4993856448
model-00029-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca4312a56abf0c0827dfa8d75ac382cf8b5ff0cc5cc841555f6006a5aa1d641
3
+ size 4998108016
model-00032-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0373e06cbc467541dc203a6dc098e33652b3632329a4058ebdd242a79281f8
3
+ size 4993856520
model-00033-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88243f4966ca7188cd939528815b9ab8946f34d3a902398fe9126cb04a3b383
3
+ size 4998108016
model-00037-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cabc6ab4a3ff425f63800a0ba36e22f723e9c76787f68e83160c5f677b85e04
3
+ size 4996447680
model-00038-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ccc3606bfc95f4f5580a56d8aecf407fc329c6c154f1609e3376c3989274659
3
+ size 4993849056
model-00039-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc1bd7b99e5f933f39b533edf4b2361aec033e85f43b237d8d31861585610eb
3
+ size 4993856392
model-00040-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67546927b12db4f69ae35f38ae536bd8be232e2dfdfa4cc904fb9d8f2320488b
3
+ size 4998108040
model-00041-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15f12ee749f7e8efcbb47f7b7d22d1d14665f09832f9819a679b1ec29c1c75a
3
+ size 4993856200
model-00042-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896067cc2422fd8604bbc06c49f668d1cf50844949235f7b5df73776b5ff529e
3
+ size 4993849056
model-00043-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7dc4b5627c8fc35182b2c03e6d34d6ef19a99f07041e80c36a848068cd8443
3
+ size 4993856464
model-00046-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0609d1b3252de2cdc34ac259b0e05d493b3bc267aa95d02aa35777742bd4ef
3
+ size 4993849096
model-00047-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133dba4e5153703d3da553f95a1d2366d95a045bb0d158554e472cba61593d79
3
+ size 4993856536
model-00048-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d536c853663efecbfaefd9b252e574efccbdc1ee58abb3f1a03e213fb1c4b515
3
+ size 4998108024
model-00050-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cdd441373b359266265c2b60150d8842d80a6329b6948daf553f429e8e9308
3
+ size 4993849168
model-00052-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f4b45672af16071446ce075dd116f40a4d399b568d1910473397a0cebb0726
3
+ size 4993819280
model-00053-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb8d6523ff5c771740ebdf7bebfc3abd69a464716255a76e47dea4aab3dd7a3
3
+ size 4993849056
model-00054-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e111f7b3a7ee985636c7b68048bbd96d6e4f304df5a96c45fd04064ab2ce0e9
3
+ size 4993856416
model-00056-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db1c90f6873bc25d5f8be2752c17b7190110a46459570ad228954baf26ef058
3
+ size 4993856216
model-00058-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6bc828b7e2dab028b48c25bfe0be2eeaa48ae90847a2c5bfdcf2ccaa87f1e7
3
+ size 4993856488
model-00059-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd82008bf14ff2a0604ae74f8b34f8a572492f9cdb173bd3424d7a9a7587f66c
3
+ size 4998108024
model-00060-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7cb67852cced1215bb7de9e59483cc799cb413743845827a573cc405812bdd
3
+ size 4993856224
model-00062-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b6afc7f6a634e6ff4f177bdf36f5424994bd45609bbdd802564e877ad5b3f3
3
+ size 4993856560
model-00066-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3256edeb5623a5efc8a6e2a13cc4e2b2e95dd5944679abc7dd5c5d7ae818fc4a
3
+ size 4998108080
model-00067-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df59874d305d1f0adc5b795507f8cf5608140f64cc2408a02d67ca19fc77d15
3
+ size 4993856168
model-00068-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74ce6588b8a563ebd7c622c66e721349e40f6569810399e65dcf048934348bd
3
+ size 4993856224
model-00071-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ed26cd236b457118d6e92bf5852dc6f70737a08c9f4123da69d64d1050748e
3
+ size 4993856224
model-00072-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a23ca9543bfde43e89940d0dbed3f7c397b9983f7c29cbf06c7e82ef3a4681c8
3
+ size 4001147496
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*mlp.gate$', 're:.*mlp.shared_expert_gate$', 're:.*linear_attn.*']
6
+ scheme: FP8_DYNAMIC
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