Hugging Face's logo

unsloth
/
GLM-5.1

Safetensors
glm_moe_dsa
Model card Files
xet
 Community
danielhanchen commited on
Commit
a5cfcc6
·
verified ·
1 Parent(s): f276a9c

Add files using upload-large-folder tool

Browse files
Files changed (49) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +117 -0
  3. config.json +59 -0
  4. generation_config.json +12 -0
  5. model-00007-of-00282.safetensors +3 -0
  6. model-00017-of-00282.safetensors +3 -0
  7. model-00020-of-00282.safetensors +3 -0
  8. model-00021-of-00282.safetensors +3 -0
  9. model-00024-of-00282.safetensors +3 -0
  10. model-00040-of-00282.safetensors +3 -0
  11. model-00044-of-00282.safetensors +3 -0
  12. model-00049-of-00282.safetensors +3 -0
  13. model-00052-of-00282.safetensors +3 -0
  14. model-00056-of-00282.safetensors +3 -0
  15. model-00057-of-00282.safetensors +3 -0
  16. model-00066-of-00282.safetensors +3 -0
  17. model-00067-of-00282.safetensors +3 -0
  18. model-00070-of-00282.safetensors +3 -0
  19. model-00073-of-00282.safetensors +3 -0
  20. model-00074-of-00282.safetensors +3 -0
  21. model-00075-of-00282.safetensors +3 -0
  22. model-00077-of-00282.safetensors +3 -0
  23. model-00078-of-00282.safetensors +3 -0
  24. model-00079-of-00282.safetensors +3 -0
  25. model-00083-of-00282.safetensors +3 -0
  26. model-00084-of-00282.safetensors +3 -0
  27. model-00087-of-00282.safetensors +3 -0
  28. model-00089-of-00282.safetensors +3 -0
  29. model-00092-of-00282.safetensors +3 -0
  30. model-00097-of-00282.safetensors +3 -0
  31. model-00104-of-00282.safetensors +3 -0
  32. model-00111-of-00282.safetensors +3 -0
  33. model-00112-of-00282.safetensors +3 -0
  34. model-00124-of-00282.safetensors +3 -0
  35. model-00128-of-00282.safetensors +3 -0
  36. model-00130-of-00282.safetensors +3 -0
  37. model-00134-of-00282.safetensors +3 -0
  38. model-00146-of-00282.safetensors +3 -0
  39. model-00148-of-00282.safetensors +3 -0
  40. model-00150-of-00282.safetensors +3 -0
  41. model-00152-of-00282.safetensors +3 -0
  42. model-00153-of-00282.safetensors +3 -0
  43. model-00156-of-00282.safetensors +3 -0
  44. model-00164-of-00282.safetensors +3 -0
  45. model-00174-of-00282.safetensors +3 -0
  46. model-00179-of-00282.safetensors +3 -0
  47. model-00182-of-00282.safetensors +3 -0
  48. model.safetensors.index.json +0 -0
  49. tokenizer_config.json +33 -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 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- if tools -%}
3
+ {%- macro tool_to_json(tool) -%}
4
+ {%- set ns_tool = namespace(first=true) -%}
5
+ {{ '{' -}}
6
+ {%- for k, v in tool.items() -%}
7
+ {%- if k != 'defer_loading' and k != 'strict' -%}
8
+ {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
9
+ {%- set ns_tool.first = false -%}
10
+ "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
11
+ {%- endif -%}
12
+ {%- endfor -%}
13
+ {{- '}' -}}
14
+ {%- endmacro -%}
15
+ <|system|>
16
+ # Tools
17
+
18
+ You may call one or more functions to assist with the user query.
19
+
20
+ You are provided with function signatures within <tools></tools> XML tags:
21
+ <tools>
22
+ {% for tool in tools %}
23
+ {%- if 'function' in tool -%}
24
+ {%- set tool = tool['function'] -%}
25
+ {%- endif -%}
26
+ {% if tool.defer_loading is not defined or not tool.defer_loading %}
27
+ {{ tool_to_json(tool) }}
28
+ {% endif %}
29
+ {% endfor %}
30
+ </tools>
31
+
32
+ For each function call, output the function name and arguments within the following XML format:
33
+ <tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
34
+ {%- macro visible_text(content) -%}
35
+ {%- if content is string -%}
36
+ {{- content }}
37
+ {%- elif content is iterable and content is not mapping -%}
38
+ {%- for item in content -%}
39
+ {%- if item is mapping and item.type == 'text' -%}
40
+ {{- item.text }}
41
+ {%- elif item is string -%}
42
+ {{- item }}
43
+ {%- endif -%}
44
+ {%- endfor -%}
45
+ {%- else -%}
46
+ {{- content }}
47
+ {%- endif -%}
48
+ {%- endmacro -%}
49
+ {%- set ns = namespace(last_user_index=-1, thinking_indices='') -%}
50
+ {%- for m in messages %}
51
+ {%- if m.role == 'user' %}
52
+ {%- set ns.last_user_index = loop.index0 -%}
53
+ {%- elif m.role == 'assistant' %}
54
+ {%- if m.reasoning_content is string %}
55
+ {%- set ns.thinking_indices = ns.thinking_indices ~ ',' ~ ns.last_user_index ~ ',' -%}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- set ns.has_thinking = false -%}
60
+ {%- for m in messages -%}
61
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%}
62
+ {%- elif m.role == 'assistant' -%}
63
+ <|assistant|>
64
+ {%- set content = visible_text(m.content) %}
65
+ {%- if m.reasoning_content is string %}
66
+ {%- set reasoning_content = m.reasoning_content %}
67
+ {%- elif '</think>' in content %}
68
+ {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
69
+ {%- set content = content.split('</think>')[-1] %}
70
+ {%- elif loop.index0 > ns.last_user_index and not (enable_thinking is defined and not enable_thinking) %}
71
+ {%- set reasoning_content = '' %}
72
+ {%- elif loop.index0 < ns.last_user_index and ns.has_thinking %}
73
+ {%- set reasoning_content = '' %}
74
+ {%- endif %}
75
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
76
+ {{ '<think>' + reasoning_content + '</think>'}}
77
+ {%- else -%}
78
+ {{ '</think>' }}
79
+ {%- endif -%}
80
+ {%- if content.strip() -%}
81
+ {{ content.strip() }}
82
+ {%- endif -%}
83
+ {% if m.tool_calls %}
84
+ {% for tc in m.tool_calls %}
85
+ {%- if tc.function %}
86
+ {%- set tc = tc.function %}
87
+ {%- endif %}
88
+ {{- '<tool_call>' + tc.name -}}
89
+ {% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
90
+ {% endif %}
91
+ {%- elif m.role == 'tool' -%}
92
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
93
+ {{- '<|observation|>' -}}
94
+ {%- endif %}
95
+ {%- if m.content is string -%}
96
+ {{- '<tool_response>' + m.content + '</tool_response>' -}}
97
+ {%- else -%}
98
+ {{- '<tool_response><tools>\n' -}}
99
+ {% for tr in m.content %}
100
+ {%- for tool in tools -%}
101
+ {%- if 'function' in tool -%}
102
+ {%- set tool = tool['function'] -%}
103
+ {%- endif -%}
104
+ {%- if tool.name == tr.name -%}
105
+ {{- tool_to_json(tool) + '\n' -}}
106
+ {%- endif -%}
107
+ {%- endfor -%}
108
+ {%- endfor -%}
109
+ {{- '</tools></tool_response>' -}}
110
+ {% endif -%}
111
+ {%- elif m.role == 'system' -%}
112
+ <|system|>{{ visible_text(m.content) }}
113
+ {%- endif -%}
114
+ {%- endfor -%}
115
+ {%- if add_generation_prompt -%}
116
+ <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
117
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GlmMoeDsaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": [
9
+ 154820,
10
+ 154827,
11
+ 154829
12
+ ],
13
+ "ep_size": 1,
14
+ "first_k_dense_replace": 3,
15
+ "hidden_act": "silu",
16
+ "head_dim": 64,
17
+ "hidden_size": 6144,
18
+ "index_head_dim": 128,
19
+ "index_n_heads": 32,
20
+ "index_topk": 2048,
21
+ "indexer_rope_interleave": true,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 12288,
24
+ "kv_lora_rank": 512,
25
+ "max_position_embeddings": 202752,
26
+ "moe_intermediate_size": 2048,
27
+ "moe_layer_freq": 1,
28
+ "model_type": "glm_moe_dsa",
29
+ "n_group": 1,
30
+ "n_routed_experts": 256,
31
+ "n_shared_experts": 1,
32
+ "norm_topk_prob": true,
33
+ "num_attention_heads": 64,
34
+ "num_experts_per_tok": 8,
35
+ "num_hidden_layers": 78,
36
+ "num_key_value_heads": 64,
37
+ "num_nextn_predict_layers": 1,
38
+ "pad_token_id": 154820,
39
+ "pretraining_tp": 1,
40
+ "q_lora_rank": 2048,
41
+ "qk_head_dim": 256,
42
+ "qk_nope_head_dim": 192,
43
+ "qk_rope_head_dim": 64,
44
+ "rms_norm_eps": 1e-05,
45
+ "rope_interleave": true,
46
+ "rope_parameters": {
47
+ "rope_theta": 1000000,
48
+ "rope_type": "default"
49
+ },
50
+ "routed_scaling_factor": 2.5,
51
+ "scoring_func": "sigmoid",
52
+ "tie_word_embeddings": false,
53
+ "topk_group": 1,
54
+ "topk_method": "noaux_tc",
55
+ "transformers_version": "5.4.0",
56
+ "use_cache": true,
57
+ "v_head_dim": 256,
58
+ "vocab_size": 154880
59
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 154820,
5
+ 154827,
6
+ 154829
7
+ ],
8
+ "pad_token_id": 154820,
9
+ "temperature": 1.0,
10
+ "top_p": 0.95,
11
+ "transformers_version": "5.4.0"
12
+ }
model-00007-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84b6d1726a4fa595ecf43d8e1e9c2607284410d38cc1e2ab03e0db74d590b29
3
+ size 5360347320
model-00017-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4367ef17cf64604103c10de137caf82587a463158e98ac6073c22f5323563e2
3
+ size 5360347320
model-00020-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f127a32f25d7a5f42d7d0cc5f13c0604c3ee3e1cceaf831238027b654205a862
3
+ size 5359985400
model-00021-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2ea4190e8f27cc696d2c13e6669a3d41b619963787b5aa8dd4301c4ba2a967
3
+ size 5360347320
model-00024-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503df0c91788dcdd78e32a3cef88fa2602d226ab1fda6edf08806c46590fd308
3
+ size 5359985464
model-00040-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809e3af5cebc911a15475c661a29d74e0769927aba4f1c11a51b7ccfa3146658
3
+ size 5360347320
model-00044-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428f9201448c9b86a6eba9b1e2cfa6e74dc368f28e944f08375f4d40834f77bc
3
+ size 5360347320
model-00049-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3877974845320f94a4e4b234c65bdc213c2211b0ebb113a26758458471ed6fe
3
+ size 5363494080
model-00052-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c0868d92b2cfba99b5a6ff20a0693e087669689e48bea4957f680fc94f1cda
3
+ size 5360347224
model-00056-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a28233bc2220d7ba8e6af9d027dfcace5a6c01c5bae84e5ef4c5908e979bd04
3
+ size 5360347160
model-00057-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:746ad35970c7c0d4cad62e4124934883681a6c60243e4ea952e5b836491ef697
3
+ size 5359985400
model-00066-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bbc2967ed75920c04aa27415e5f11d54ff2b7691ceb910d7560e6ed7b9436ac
3
+ size 5360347320
model-00067-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b67861a75b8fa0892c6db22f6980c8c1d8a47ce6e19e038547134e1b10d36a
3
+ size 5360347168
model-00070-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba225f9c1df2be0120bb1077df3b2c96f3bcca3de6f053e9b0fd866be055df9
3
+ size 5360347312
model-00073-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5124711d52eb9976778c5896998577deb0711f080588c6a4f247333564e399f0
3
+ size 5360347312
model-00074-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df655eb121bb1210e6f720d60e2d73a42952e0933b31c1a8a31e04d30739a6c5
3
+ size 5360347248
model-00075-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b8fc7b2750a567de9ee984aeb6fa0f8d2e2e2d61a90e60a14e8e65b8ecc774
3
+ size 5359985280
model-00077-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a66a9ce83780d9ca82bd4a81a6cf9ac5eeec1fbce4cbc6d53171ea7c52c78ba9
3
+ size 5360347104
model-00078-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e90264fe9ea3a1268f5650e51486d318a02f8860f840dd27f058cf9b0cffa4
3
+ size 5360346968
model-00079-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c06b534116e32c2a4771453ac9150ec9a4bdb15b380dd8ab576857926f881d
3
+ size 5359985256
model-00083-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224796602a6703b225f87459a565f88ff3753a5686386fd45ca31a04ffa3f039
3
+ size 5359985432
model-00084-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ee7929c3a6a1c167a0d85df37094523e9b4dff12f8925c8b8afae981cacf91
3
+ size 5360347312
model-00087-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f13445a7d531f2b4371281ecaf38af47a9b300dfd116aae46a32f59e2edbf35
3
+ size 5360347320
model-00089-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16bc2e0f8891f24082001560622d7965a814d2dd37e395d35e4a719d5c2ef90
3
+ size 5360347192
model-00092-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53e890e89e849df560949a6988a61e86c73ff6848361e5882e5d69088ca281a7
3
+ size 5360347312
model-00097-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0e24b0ddcd9123fb09dd51421d99b39f976181aa9e0c4130f0ca350473cf5b
3
+ size 5359985296
model-00104-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8e53602ec30ac34e17d2e7fa7744cfe1aed9d66bc6c1f17b57f8f17577e2ca
3
+ size 5360347136
model-00111-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9323fa8011ddbdf2b1f2590c6409f972768ed729975a316036b561272538a59b
3
+ size 5360347224
model-00112-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8db95639b26759b19186ba02a44046d037d0332eb631fef6b39b99c3fda0ae4
3
+ size 5359985336
model-00124-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a965b27cfddefe942ebd165d411b5c862dc6f23b3c9b457911c0e08062fb3e0
3
+ size 5360347320
model-00128-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2b8e3859bc19559e48aa04755bef2cc25684454ee328dea27745be8231a85a
3
+ size 5360347320
model-00130-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d986b71db2f75d50c2f3eae1087cb72ded3ad48fb8f7717ec146cc2f0effa8b4
3
+ size 5360347104
model-00134-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9550d460e928efd8f320298072f197bf00bac127e9339a68425ff1c99567f993
3
+ size 5359985312
model-00146-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dddd5f9b740fe073939b288a94a58e4cc332453be462b037c6cb84b39120c479
3
+ size 5360347320
model-00148-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688c9329aaa9652daeb3eb86b2b5b090763f29e5424e1bb520d79242eb208bf2
3
+ size 5360347192
model-00150-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88169f9b03b709e0c3af1204db2fcc18acd05620127e6c36231792130ffb77ee
3
+ size 5360347320
model-00152-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f123f76cdb5388b3c02971a1d887343de4165b9bf51df54c5f196f347819cef
3
+ size 5360347120
model-00153-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98083eac44021dedbecd4aa30d659e71d43da17aaba4bc220931a4f09e7194a9
3
+ size 5359985432
model-00156-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec650c72f804313b326c108e474443b08436d16cc3c1ecb456bc9bb80f2bd15
3
+ size 5359985288
model-00164-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15de95274bdb8e085f97d4ba3751dd8e1c863a2b4a44e2f2e01b68ed52140d56
3
+ size 5359985424
model-00174-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784f61f5008aeb15065f53af4c06bb5c4471e78cda50833a862038687f8b1d45
3
+ size 5360347152
model-00179-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ec4f2c1e23417a2108ad439266f6d63b2d28c5ce81b2f307acac9543028134
3
+ size 5359985472
model-00182-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256e921e37f9ffee7a1872d69f77a0159b7e02b23203b18093feab759a75fbc4
3
+ size 5359985328
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": false,
4
+ "do_lower_case": false,
5
+ "eos_token": "<|endoftext|>",
6
+ "extra_special_tokens": [
7
+ "<|endoftext|>",
8
+ "[MASK]",
9
+ "[gMASK]",
10
+ "[sMASK]",
11
+ "<sop>",
12
+ "<eop>",
13
+ "<|system|>",
14
+ "<|user|>",
15
+ "<|assistant|>",
16
+ "<|observation|>",
17
+ "<|begin_of_image|>",
18
+ "<|end_of_image|>",
19
+ "<|begin_of_video|>",
20
+ "<|end_of_video|>",
21
+ "<|begin_of_audio|>",
22
+ "<|end_of_audio|>",
23
+ "<|begin_of_transcription|>",
24
+ "<|end_of_transcription|>"
25
+ ],
26
+ "is_local": true,
27
+ "model_max_length": 202752,
28
+ "model_specific_special_tokens": {},
29
+ "pad_token": "<|endoftext|>",
30
+ "padding_side": "left",
31
+ "remove_space": false,
32
+ "tokenizer_class": "TokenizersBackend"
33
+ }