Hugging Face's logo

syntheticlab
/
GLM-4.5-FP8

Safetensors
glm4_moe
compressed-tensors
Model card Files
xet
Community
reissbaker commited on
Commit
d3f3bd9
·
verified ·
1 Parent(s): d90e0fd

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-00001-of-00072.safetensors +3 -0
  6. model-00002-of-00072.safetensors +3 -0
  7. model-00003-of-00072.safetensors +3 -0
  8. model-00004-of-00072.safetensors +3 -0
  9. model-00005-of-00072.safetensors +3 -0
  10. model-00006-of-00072.safetensors +3 -0
  11. model-00007-of-00072.safetensors +3 -0
  12. model-00010-of-00072.safetensors +3 -0
  13. model-00012-of-00072.safetensors +3 -0
  14. model-00013-of-00072.safetensors +3 -0
  15. model-00014-of-00072.safetensors +3 -0
  16. model-00016-of-00072.safetensors +3 -0
  17. model-00017-of-00072.safetensors +3 -0
  18. model-00020-of-00072.safetensors +3 -0
  19. model-00021-of-00072.safetensors +3 -0
  20. model-00022-of-00072.safetensors +3 -0
  21. model-00026-of-00072.safetensors +3 -0
  22. model-00029-of-00072.safetensors +3 -0
  23. model-00031-of-00072.safetensors +3 -0
  24. model-00032-of-00072.safetensors +3 -0
  25. model-00037-of-00072.safetensors +3 -0
  26. model-00042-of-00072.safetensors +3 -0
  27. model-00045-of-00072.safetensors +3 -0
  28. model-00048-of-00072.safetensors +3 -0
  29. model-00050-of-00072.safetensors +3 -0
  30. model-00051-of-00072.safetensors +3 -0
  31. model-00052-of-00072.safetensors +3 -0
  32. model-00056-of-00072.safetensors +3 -0
  33. model-00059-of-00072.safetensors +3 -0
  34. model-00060-of-00072.safetensors +3 -0
  35. model-00061-of-00072.safetensors +3 -0
  36. model-00062-of-00072.safetensors +3 -0
  37. model-00063-of-00072.safetensors +3 -0
  38. model-00064-of-00072.safetensors +3 -0
  39. model-00065-of-00072.safetensors +3 -0
  40. model-00066-of-00072.safetensors +3 -0
  41. model-00067-of-00072.safetensors +3 -0
  42. model-00068-of-00072.safetensors +3 -0
  43. model-00069-of-00072.safetensors +3 -0
  44. model-00070-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
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
+ "eos_token_id": [
8
+ 151329,
9
+ 151336,
10
+ 151338
11
+ ],
12
+ "first_k_dense_replace": 3,
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 5120,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 12288,
18
+ "max_position_embeddings": 131072,
19
+ "model_type": "glm4_moe",
20
+ "moe_intermediate_size": 1536,
21
+ "n_group": 1,
22
+ "n_routed_experts": 160,
23
+ "n_shared_experts": 1,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 96,
26
+ "num_experts_per_tok": 8,
27
+ "num_hidden_layers": 92,
28
+ "num_key_value_heads": 8,
29
+ "num_nextn_predict_layers": 1,
30
+ "pad_token_id": 151329,
31
+ "partial_rotary_factor": 0.5,
32
+ "quantization_config": {
33
+ "config_groups": {
34
+ "group_0": {
35
+ "format": "float-quantized",
36
+ "input_activations": {
37
+ "actorder": null,
38
+ "block_structure": null,
39
+ "dynamic": true,
40
+ "group_size": null,
41
+ "num_bits": 8,
42
+ "observer": null,
43
+ "observer_kwargs": {},
44
+ "strategy": "token",
45
+ "symmetric": true,
46
+ "type": "float"
47
+ },
48
+ "output_activations": null,
49
+ "targets": [
50
+ "Linear"
51
+ ],
52
+ "weights": {
53
+ "actorder": null,
54
+ "block_structure": null,
55
+ "dynamic": false,
56
+ "group_size": null,
57
+ "num_bits": 8,
58
+ "observer": "minmax",
59
+ "observer_kwargs": {},
60
+ "strategy": "channel",
61
+ "symmetric": true,
62
+ "type": "float"
63
+ }
64
+ }
65
+ },
66
+ "format": "float-quantized",
67
+ "global_compression_ratio": null,
68
+ "ignore": [
69
+ "lm_head"
70
+ ],
71
+ "kv_cache_scheme": null,
72
+ "quant_method": "compressed-tensors",
73
+ "quantization_status": "compressed",
74
+ "sparsity_config": {},
75
+ "transform_config": {},
76
+ "version": "0.11.0"
77
+ },
78
+ "rms_norm_eps": 1e-05,
79
+ "rope_scaling": null,
80
+ "rope_theta": 1000000,
81
+ "routed_scaling_factor": 2.5,
82
+ "tie_word_embeddings": false,
83
+ "topk_group": 1,
84
+ "torch_dtype": "bfloat16",
85
+ "transformers_version": "4.55.2",
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": "4.55.2"
10
+ }
model-00001-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d48ce060551ce29dc2535dd222e280c0157e756facf137c37a05d09fc2ddbbd2
3
+ size 4993429864
model-00002-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e38eb905e9e823b4e86fa1302bb9dddd4315f8a7017400555463e1eaa7057c1
3
+ size 4993855232
model-00003-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e739f8e595cd4ea69630a256957f7ca5da6a97a07b808402927e007aa55b29d5
3
+ size 4998106784
model-00004-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c965084dc1983739fd41e22f0a94ac1359a02d5d3ecf1f772b92fb2414d32462
3
+ size 4993854968
model-00005-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4680bec9ff90a69dc2cc8f82c11328a4e97316373a31db67191fb45bf0ada4
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:c7ba8300fec303d21cc43ac29772e9068cc7a3dbae968763715f099360a97214
3
+ size 4993855304
model-00007-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2561af72be2a0d4e8e0c6fffc9a0837fcd967912b45220c2b182cba1f8148f3
3
+ size 4998107648
model-00010-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93a7c576d613f2bca0f14a61303289d758fa974fe369e6b994b6c02ae0c1f59
3
+ size 4998108080
model-00012-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c831d8211251117e0ea2bfe77bb719df03b8399dbda468bb5acd2421b0de5058
3
+ size 4993856224
model-00013-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35909aef1a6d2202c72b70e73b2e4ac38f7c0733084c347cd2d22f22088788d6
3
+ size 4993849264
model-00014-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1db08eb27ad8d857adbf03e18a516f2600f447c99cb21800229cf9bb3be839
3
+ size 4998108024
model-00016-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3e6c5b4cb70dd05e782ede459a70ebde6babe4943c8b8743f05da9dbf26d73
3
+ size 4993856232
model-00017-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae99d65c69d315c46505c8e85e5e8393b530c8831d90a95bdd55a2e880d9aba3
3
+ size 4993849336
model-00020-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc16b090c3bb6492234d0f2c2dd31fe5306f54eb51dee75e754c78a035c7c0bd
3
+ size 4993856304
model-00021-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17fd987e550890c7b2980fd2a8c166d8d4965dda6159c5592f8308e68f71f0a6
3
+ size 4993849408
model-00022-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999379c13b2e54593fef5b5518221ed1652652cf30b876973dc9e63da1fc3f7c
3
+ size 4998108040
model-00026-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffe3260c6cdfa39c979ee25d9865bbc6e6ef087387d1bd1be2b19e32398da48
3
+ size 4993849016
model-00029-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6035323c91be07dd7e03270625d567f4b1f604be548988f40ab8b44b109e79c7
3
+ size 4998108016
model-00031-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62a82f249fb1eb5c9d770f9f4ada5fcda54303ba30a3d65374d188b5628662a
3
+ size 4993856256
model-00032-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae235cc6070e9acc9e0b2b1d116f553ac9e15cedd26c5b5e0988756f9562df3
3
+ size 4993856520
model-00037-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a8e142677b4c4c2bf7aa97b788685ac7683c600ceb309d9073d2471f3baba3
3
+ size 4996447680
model-00042-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd8a08e9630ae1fc7f04af5072e8f3d65f4bbe549d35da11541ee818253865ef
3
+ size 4993849056
model-00045-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de051d38a34304e1523a9b6e16b6ffbcaa3ed884291182f87e232a9f62745c9d
3
+ size 4993856224
model-00048-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27dea266e39e99d166005d8c34c9370eedf18763e5439ac76fb94bf1570e1246
3
+ size 4998108024
model-00050-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3607d3dc6af36b9430731c04e5a7a1bb8c1af8b80955d0309e7ef52675d2e60c
3
+ size 4993849168
model-00051-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5319a2598f729108c733b59a6f8874582951f044801f8f82a44fd0214215d520
3
+ size 4990277320
model-00052-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19e2c697e2f4567dc2d5e8623c231672b50da43ba6e99a0b84ebec272a6471b
3
+ size 4993819280
model-00056-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd0466c956a4dc8f95d6a991b0b210dafbcc3cafd650efac65ed705b10e6156
3
+ size 4993856216
model-00059-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09325a7d38067991a61bdd4e3a5558c3573fa244476916102333eec6878589e
3
+ size 4998108024
model-00060-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a55ab3af5aceb5a331850a0d702e4341f9899289b60c1dd65ea04c338eaae6
3
+ size 4993856224
model-00061-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d1c1418fb02eab712b1e21e98289ba1a7d84f01fc02a5a2225f1735d4af1a2
3
+ size 4993849120
model-00062-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e6c389cb7b0a8222f5fe08e2581f598f8a650e8993feaa151e90b6874b70ec
3
+ size 4993856560
model-00063-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb43d9d6bb92c48c5afec722637b4e808ad847e3fa177f5b3ffc0b38cbbb8f2d
3
+ size 4998108024
model-00064-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2370a4d40b2728d0c80d55ef23b519715c53d0e0febce72aa25a8bcb34a59f
3
+ size 4993856224
model-00065-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91addc592434e2a9f6b57c996414d093fde499c23d0702f490bcc12753d702d5
3
+ size 4993849192
model-00066-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4191713a2476ccfdc7068e95280216a0c0f02ce32351cb7f731d5cb2b73907
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:c3b9a15fbb0a85c3fed9c8378425eabd7103337fc07b0ee7b00f8b0a29fe1bc9
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:eee33f70cec9f93cceb11b2d358d06484e21c8f83bae2e8a43785d4e19187ae4
3
+ size 4993856224
model-00069-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf041a1d9c578b806a0f65e2c35a5e96d819805d168a5b343a1a3c49275510e
3
+ size 4993849264
model-00070-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe91c7d3a69c250c6f12b0c0c6ff8d2630ec1e3ac7c579093be0b6f2c7d651e
3
+ size 4998108024
model-00071-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061f76ef82bb7fadcdf48b59819b2262d6d34305914fc1144cb7ec414cee2b8b
3
+ size 3503839048
model-00072-of-00072.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf648ab9c4c78b3573f69b6868e0e74476b856418cca0bfab91277346b63cd1
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 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
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