Hugging Face's logo

inference-optimization
/
GLM-4.6-NVFP4

Safetensors
glm4_moe
8-bit precision
compressed-tensors
Model card Files
xet
Community
Shubhra Pandit commited on
Commit
2c00afe
·
0 Parent(s):

Upload model files

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 +39 -0
  2. 5daab62106b72a49/gpqa:diamond|0/e4d6395c589ea279/GENERATIVE.parquet +3 -0
  3. chat_template.jinja +103 -0
  4. config.json +89 -0
  5. generation_config.json +10 -0
  6. model-00001-of-00041.safetensors +3 -0
  7. model-00002-of-00041.safetensors +3 -0
  8. model-00003-of-00041.safetensors +3 -0
  9. model-00004-of-00041.safetensors +3 -0
  10. model-00005-of-00041.safetensors +3 -0
  11. model-00006-of-00041.safetensors +3 -0
  12. model-00007-of-00041.safetensors +3 -0
  13. model-00008-of-00041.safetensors +3 -0
  14. model-00009-of-00041.safetensors +3 -0
  15. model-00010-of-00041.safetensors +3 -0
  16. model-00011-of-00041.safetensors +3 -0
  17. model-00012-of-00041.safetensors +3 -0
  18. model-00013-of-00041.safetensors +3 -0
  19. model-00014-of-00041.safetensors +3 -0
  20. model-00015-of-00041.safetensors +3 -0
  21. model-00016-of-00041.safetensors +3 -0
  22. model-00017-of-00041.safetensors +3 -0
  23. model-00018-of-00041.safetensors +3 -0
  24. model-00019-of-00041.safetensors +3 -0
  25. model-00020-of-00041.safetensors +3 -0
  26. model-00021-of-00041.safetensors +3 -0
  27. model-00022-of-00041.safetensors +3 -0
  28. model-00023-of-00041.safetensors +3 -0
  29. model-00024-of-00041.safetensors +3 -0
  30. model-00025-of-00041.safetensors +3 -0
  31. model-00026-of-00041.safetensors +3 -0
  32. model-00027-of-00041.safetensors +3 -0
  33. model-00028-of-00041.safetensors +3 -0
  34. model-00029-of-00041.safetensors +3 -0
  35. model-00030-of-00041.safetensors +3 -0
  36. model-00031-of-00041.safetensors +3 -0
  37. model-00032-of-00041.safetensors +3 -0
  38. model-00033-of-00041.safetensors +3 -0
  39. model-00034-of-00041.safetensors +3 -0
  40. model-00035-of-00041.safetensors +3 -0
  41. model-00036-of-00041.safetensors +3 -0
  42. model-00037-of-00041.safetensors +3 -0
  43. model-00038-of-00041.safetensors +3 -0
  44. model-00039-of-00041.safetensors +3 -0
  45. model-00040-of-00041.safetensors +3 -0
  46. model-00041-of-00041.safetensors +3 -0
  47. model.safetensors.index.json +3 -0
  48. recipe.yaml +6 -0
  49. special_tokens_map.json +40 -0
  50. tokenizer.json +3 -0
.gitattributes ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+
38
+ *.index.json filter=lfs diff=lfs merge=lfs -text
39
+ *.index.json filter=lfs diff=lfs merge=lfs -text
5daab62106b72a49/gpqa:diamond|0/e4d6395c589ea279/GENERATIVE.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f44667fce2968c4b3295cccc8c043be1033594801b8c82d011fd1c3392ed4f2
3
+ size 5582871
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": "nvfp4-pack-quantized",
37
+ "input_activations": {
38
+ "actorder": null,
39
+ "block_structure": null,
40
+ "dynamic": "local",
41
+ "group_size": 16,
42
+ "num_bits": 4,
43
+ "observer": "static_minmax",
44
+ "observer_kwargs": {},
45
+ "strategy": "tensor_group",
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": 16,
58
+ "num_bits": 4,
59
+ "observer": "memoryless_minmax",
60
+ "observer_kwargs": {},
61
+ "strategy": "tensor_group",
62
+ "symmetric": true,
63
+ "type": "float"
64
+ }
65
+ }
66
+ },
67
+ "format": "nvfp4-pack-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": "0.12.3.dev31+gb019b89"
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": "4.57.3",
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": "4.57.3"
10
+ }
model-00001-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb0c08db2d0122a5298bf7b90551f985f08f99c32b13f6613098d5515904ad0
3
+ size 4998659536
model-00002-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350f7920e6a114c7e5a1ba6f0cde26bc3a33b3625367bdc5115a17a1c5b322be
3
+ size 4996788968
model-00003-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b6e5b7fcdd74c008d8810ce1286ff1ac0c58c6240fb7ba8dca64643f992f66
3
+ size 4996789328
model-00004-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b8a83ebaed2a50a4f0cb852eb28ec51da8b3e64a07d55b855ccea925b89da1
3
+ size 4999948944
model-00005-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbb15f6f5f332b4fd5ef70540812dc03380b7a534ed4ad45a6d075e7d2858cd
3
+ size 4996793352
model-00006-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85c6ffe0bf8bc05e7a9793896375c326d547333d351cbd346ea6cb271d4dd4a
3
+ size 4996793392
model-00007-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e3e9d1ac7b05e0b3dcdce69ff25eb142fb255b4b42d7f79863fec030156062
3
+ size 4996793800
model-00008-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbe0c5ae5f2b9f999272a711263b71ecfcd1b6c4dbf5045ea936d017cad7b95
3
+ size 4999951528
model-00009-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2debb3311a0d4d2dbd5706c851773d3d1488bf8f046c2a84b40d1c6ff608ded
3
+ size 4996793384
model-00010-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529bbef410d198aba89498c6be5edb32c78c01913e90d5309e3818621ad84098
3
+ size 4996793392
model-00011-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf8c7b8fec1b12819752bc69a44c3231a59a9f75f7023fe862699fa3df43edc0
3
+ size 4996793848
model-00012-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896b2a5785ab03f046ba3f3cc7991f63a38330a5088b0ccafdf6ba89433f3f6e
3
+ size 4999951576
model-00013-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d557ccb9d987370de1d1020ef171f7cb51599f4a02f2b67a95093c16b6fc4d6
3
+ size 4996793384
model-00014-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfe96b2d69a9143cabe0cad5aaa3e1b111d625a148c5d1f67527cb49db9c24c4
3
+ size 4996793392
model-00015-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f57eaa30eeaddaa577bb9fe194e56e31b701afd6d04a03ef75169cd26dc278
3
+ size 4996793896
model-00016-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4426e0d7f7404d77d25fe9f3567c46cc79c667326e36e8ac96dda4aa732c0f
3
+ size 4999951624
model-00017-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2cd10de536ab3b957f38108b9b3c3ab3b1d84e96eed4c0c9eba54edc9399ccd
3
+ size 4996793384
model-00018-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bec4b90eff6649948c9a9e30b5964448ab93a11f60d6916849fe7494b8f6d53
3
+ size 4996793440
model-00019-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da04f0f290cb0de5226b37e1d87761007a4e9faac6678a1ce31ce25b3352abd2
3
+ size 4996793896
model-00020-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8512a9741b5e75b607f99dbf44fd4c8538d4c665f0bcfd983c2e93ab47e2ae
3
+ size 4999951648
model-00021-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:316eff11e6baf0a892bda206b8a1581a1bc1ce522cd7e576df721aa297638e2d
3
+ size 4996793384
model-00022-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8108c30af26d40950294733f9f47dd3d00e87e12afd10f9dd763bbcbd501d5
3
+ size 4996793488
model-00023-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81f4de602af3091a8bfd3c8b5b5d5fd8fa3fa291f3b1ec5e6f9150230eb12d9
3
+ size 4996793896
model-00024-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93854280e37ffe1254d5f8183d3e1cb0ca3b0a09f419dfb49bd3aadad4a1082
3
+ size 4999951600
model-00025-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866f86fd8f907ebc3673f315389f4e58150b5dab47299738e15fc5c1527cbaef
3
+ size 4996793384
model-00026-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7761a4ced316547dc48c925ee055dfecfcfb1893e0134b0bb3773211ff0a784e
3
+ size 4996793536
model-00027-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaae89a80ea3723ffb936d14485ead1769d06df19967cc64de469e7e9d885f9a
3
+ size 4996793896
model-00028-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02eb68abc986dca9024c73fdade120bd2d5af4e54bbbb8d934aeca01d343b71
3
+ size 4999951552
model-00029-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff953ad380e7ff2fb2d6404d694192b1d38bd0b4a987a18edb743aaca47e9031
3
+ size 4996793384
model-00030-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f08fb7e4fc69800fdc81d8b69c4ebc56a1355b8069485904752e36b0049e811d
3
+ size 4996793584
model-00031-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a64749f01f8407a1cdfda67374bcf020d079ca9982a91b00541ea28943a8c2
3
+ size 4996793896
model-00032-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45d0961684160708ccbe0d29572071708792f3a70287e04a029eb5cf920a8e8
3
+ size 4999951536
model-00033-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd69c40ff9097240e9a2339dbba8a1c75bd70819a7b3e6210c150cf62ce9057
3
+ size 4996793384
model-00034-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c351d8c9e624f017cc57e4907f71e7c6602c423c9c578a58053e7fe24cd45854
3
+ size 4996793632
model-00035-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ea62f4f760212b2fbedfa141e1c9d173aa27df56e2ca5e68373614a3b0924e
3
+ size 4971908776
model-00036-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0e788c2de07d5fabb0e70663dd0b17267cd34b92c0a3cc79667401d0320e28
3
+ size 4998290840
model-00037-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50f6455b2061d3cc5e53ea7118175a5b2cbb9065d283bd12ee71d58000afdd1
3
+ size 4996793384
model-00038-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef8441df081153d56c515cceb6063e662faed94ff93a7d2abd4c1cacc6d5599
3
+ size 4996793656
model-00039-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b475cfe731a269df654ecbb86e82b683d82f2961704a2f2c78dcae1bfbd12bba
3
+ size 4986681784
model-00040-of-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51dd1f4d5ee35272a106a8422f4ccb6af9f134b4d52bd07018dbfa0839c1915a
3
+ size 4389190152
model-00041-of-00041.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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23836899c31df72cd7283ede47c3930bae0c21649cd1c177d9fceadd7052ffb
3
+ size 17418078
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$']
6
+ scheme: NVFP4
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