Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- chat_template.jinja +103 -0
- config.json +54 -0
- generation_config.json +10 -0
- model-00001-of-00038.safetensors +3 -0
- model-00002-of-00038.safetensors +3 -0
- model-00003-of-00038.safetensors +3 -0
- model-00004-of-00038.safetensors +3 -0
- model-00005-of-00038.safetensors +3 -0
- model-00006-of-00038.safetensors +3 -0
- model-00007-of-00038.safetensors +3 -0
- model-00008-of-00038.safetensors +3 -0
- model-00009-of-00038.safetensors +3 -0
- model-00010-of-00038.safetensors +3 -0
- model-00011-of-00038.safetensors +3 -0
- model-00012-of-00038.safetensors +3 -0
- model-00013-of-00038.safetensors +3 -0
- model-00014-of-00038.safetensors +3 -0
- model-00015-of-00038.safetensors +3 -0
- model-00016-of-00038.safetensors +3 -0
- model-00017-of-00038.safetensors +3 -0
- model-00018-of-00038.safetensors +3 -0
- model-00019-of-00038.safetensors +3 -0
- model-00020-of-00038.safetensors +3 -0
- model-00021-of-00038.safetensors +3 -0
- model-00022-of-00038.safetensors +3 -0
- model-00023-of-00038.safetensors +3 -0
- model-00024-of-00038.safetensors +3 -0
- model-00025-of-00038.safetensors +3 -0
- model-00026-of-00038.safetensors +3 -0
- model-00027-of-00038.safetensors +3 -0
- model-00028-of-00038.safetensors +3 -0
- model-00029-of-00038.safetensors +3 -0
- model-00030-of-00038.safetensors +3 -0
- model-00031-of-00038.safetensors +3 -0
- model-00032-of-00038.safetensors +3 -0
- model-00033-of-00038.safetensors +3 -0
- model-00034-of-00038.safetensors +3 -0
- model-00035-of-00038.safetensors +3 -0
- model-00036-of-00038.safetensors +3 -0
- model-00037-of-00038.safetensors +3 -0
- model-00038-of-00038.safetensors +3 -0
- model.safetensors.index.json +3 -0
- quantization_config.json +11 -0
- special_tokens_map.json +40 -0
- tokenizer.json +3 -0
- tokenizer_config.json +325 -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 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
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 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"autoround_version": "0.6.1.dev",
|
34 |
+
"bits": 4,
|
35 |
+
"data_type": "int",
|
36 |
+
"group_size": 128,
|
37 |
+
"low_gpu_mem_usage": true,
|
38 |
+
"packing_format": "auto_round:auto_gptq",
|
39 |
+
"quant_method": "auto-round",
|
40 |
+
"seqlen": 512,
|
41 |
+
"sym": true
|
42 |
+
},
|
43 |
+
"rms_norm_eps": 1e-05,
|
44 |
+
"rope_scaling": null,
|
45 |
+
"rope_theta": 1000000,
|
46 |
+
"routed_scaling_factor": 2.5,
|
47 |
+
"tie_word_embeddings": false,
|
48 |
+
"topk_group": 1,
|
49 |
+
"torch_dtype": "bfloat16",
|
50 |
+
"transformers_version": "4.56.0.dev0",
|
51 |
+
"use_cache": true,
|
52 |
+
"use_qk_norm": true,
|
53 |
+
"vocab_size": 151552
|
54 |
+
}
|
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": "4.56.0.dev0"
|
10 |
+
}
|
model-00001-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e54a36979db368d3ada38ed1b2605332835a1ac00d0cc86c06dbbd45ab082466
|
3 |
+
size 4996956176
|
model-00002-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:818553673ce82a59a2f11981185cad5729fb3ac024760d507a08e4eaf82e4eb5
|
3 |
+
size 4999337976
|
model-00003-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e9270d15ccd6216ef02e9c43f5ba8ccbd63835464e195853d2d042644991a74
|
3 |
+
size 4998298088
|
model-00004-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:043b83becf3881f851225dadf9172eda0ad16e69974b3ad383245b88f3a9c321
|
3 |
+
size 4999340392
|
model-00005-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e842017524a663073b4d6c8a9c40781bfff13510cce285cf0ed56d1c715a4d
|
3 |
+
size 4998301832
|
model-00006-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:667c0e36f9128f64674cf4459fd0fc049984a2344171247a976bdf448cecf20a
|
3 |
+
size 4999341240
|
model-00007-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8afdd53bb8facd06803d26e01a7c5b4244c4f452a0b608ac4fd448ecad8ddb1
|
3 |
+
size 4998302000
|
model-00008-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f76209ab43239f16c29b57d93de7cc944f50ff2c94ddb4718f4ffe88dcf1a4da
|
3 |
+
size 4999341216
|
model-00009-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:085af64fd71821f82182ac8ab1b7f895f4bb1caee4d1d2640327d560734d0916
|
3 |
+
size 4999341736
|
model-00010-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7502f522a2e5825ce82fddde1f9bd5d7cec00b8555f7594f7f2ebbd90ba4faef
|
3 |
+
size 4998301504
|
model-00011-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b96a4788e1120e948c093a68552b6f191173057057698d0ec0c19b54b04743f1
|
3 |
+
size 4999341568
|
model-00012-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c8970bee0e2e5e2a54d4b05ea0937949f00e3eb4c541229995232f06e3085ac
|
3 |
+
size 4998301672
|
model-00013-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86efc13bd102b9f023495810c60dec6b5215304381ce12d722486778c936e6a4
|
3 |
+
size 4999341392
|
model-00014-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82269df69df437307b07d880227982f43890abc510971bc5c0d0c9dfbc1cab00
|
3 |
+
size 4998301848
|
model-00015-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:216bf352ce6be92cd78949134571f94fce7c8cab47458bccee1f7f18dd23ce74
|
3 |
+
size 4999341224
|
model-00016-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dc8985ccddeb0040006a2b45b7c05145cc0192bbe0a71817d7e932525c564d6
|
3 |
+
size 4998302032
|
model-00017-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf41dab92f3b7cd7f5d81ff63233cc66e1524c99449121ecf772cc29209e1224
|
3 |
+
size 4999341200
|
model-00018-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46eb573d9c0a4135df26dbdcbd3c96da7ed2f97877d67594291977fea56c3bd4
|
3 |
+
size 4999341720
|
model-00019-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15ec6ef088256f462c955bcd5306ab511474781db65b2a5989424358d23ba264
|
3 |
+
size 4998301520
|
model-00020-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dee532d2372c69d9cc596189e95667be505ac38184afd784680c7dab8829bcb
|
3 |
+
size 4999341544
|
model-00021-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c4e3a1958b569c4c8e0d1e2128890746a72724e16f75fd9d7e0383623ae5c9f
|
3 |
+
size 4998301696
|
model-00022-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edf75e137cbb35324f4e8ee77aa0a876f7888da3b91d5b9ab45143f8236f6f9f
|
3 |
+
size 4999341376
|
model-00023-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03535d1454285151aebbe1190bf3a6e54490c02c6a17f39d8ffa7f0c60abc966
|
3 |
+
size 4998301864
|
model-00024-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f6b1eec89eca40d814ee06776b8a9c4d305bf0d97627652ef06880edeb49f09
|
3 |
+
size 4999341216
|
model-00025-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:806f621dd6e1e3d61e333e85b5f394e0cf3579b12790de2bb21cb32b9b0d714f
|
3 |
+
size 4998302064
|
model-00026-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f81ab55cb2adf770ee004b6a84ffffada2eed693bc9a63fa8c41c3c636a6c995
|
3 |
+
size 4999341176
|
model-00027-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be904300635e6b6920b35d4aad6838e8b8120d680df851ef01d46470ba80f920
|
3 |
+
size 4999341704
|
model-00028-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e7d821c02e164c393acf81f7b9d8381fb822480d7402b6bf7b372e43a1f78d7
|
3 |
+
size 4998301544
|
model-00029-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:337828c729d9e9a03ada820f426060362dec4f3fa20854d0699ab0cd67235797
|
3 |
+
size 4999341528
|
model-00030-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a827e6f03b8625057a4ea5d081d61d073d9bacfe65b2da9206fdda48d29f0e9a
|
3 |
+
size 4998301712
|
model-00031-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32466536374421cd65fd50408e16ec68253db88fd4f7209cb9c6b3ff207c42fc
|
3 |
+
size 4999341360
|
model-00032-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:994ad737e33b36d17b47a5ce90a08949dbf259b7616b611ed6fcc88dd3c28034
|
3 |
+
size 4998301880
|
model-00033-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d0b5caf482575a0a8826a16198507a6f084f058f0f5e32c2892df69ef09b060
|
3 |
+
size 4999341216
|
model-00034-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e51fb71e808726c53cf9f8a6a320a38006c91973a947f35440c174ca70d6361
|
3 |
+
size 4998302080
|
model-00035-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:234a24aaa804328e3407934833e8fc0c73f16ce1eb1c7c3cf23a0bf4d4f8361f
|
3 |
+
size 4999341160
|
model-00036-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:082d7f8bcb012bcb6607dcaf0b39dd21c7321348ebd1666bdeab3f47aa9336ef
|
3 |
+
size 4999341680
|
model-00037-of-00038.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15cd2d64dd8ca843a7f2e2ce31d6db129233b78245b50ff4344eec8b15a9e660
|
3 |
+
size 4204216360
|
model-00038-of-00038.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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed5999ff809be5b1ce926793de2761372a3132faf083d6b944f4fb16b531dfd4
|
3 |
+
size 11888203
|
quantization_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"sym": true,
|
5 |
+
"data_type": "int",
|
6 |
+
"seqlen": 512,
|
7 |
+
"low_gpu_mem_usage": true,
|
8 |
+
"autoround_version": "0.6.1.dev",
|
9 |
+
"quant_method": "auto-round",
|
10 |
+
"packing_format": "auto_round:auto_gptq"
|
11 |
+
}
|
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:a6054aa7e403c8333ba41bc51e93a65351308666a8138f80334f9bd1e8a348cf
|
3 |
+
size 19970798
|
tokenizer_config.json
ADDED
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"151329": {
|
4 |
+
"content": "<|endoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"151330": {
|
12 |
+
"content": "[MASK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"151331": {
|
20 |
+
"content": "[gMASK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"151332": {
|
28 |
+
"content": "[sMASK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"151333": {
|
36 |
+
"content": "<sop>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"151334": {
|
44 |
+
"content": "<eop>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"151335": {
|
52 |
+
"content": "<|system|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"151336": {
|
60 |
+
"content": "<|user|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"151337": {
|
68 |
+
"content": "<|assistant|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"151338": {
|
76 |
+
"content": "<|observation|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"151339": {
|
84 |
+
"content": "<|begin_of_image|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"151340": {
|
92 |
+
"content": "<|end_of_image|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"151341": {
|
100 |
+
"content": "<|begin_of_video|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"151342": {
|
108 |
+
"content": "<|end_of_video|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"151343": {
|
116 |
+
"content": "<|begin_of_audio|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"151344": {
|
124 |
+
"content": "<|end_of_audio|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"151345": {
|
132 |
+
"content": "<|begin_of_transcription|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"151346": {
|
140 |
+
"content": "<|end_of_transcription|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"151347": {
|
148 |
+
"content": "<|code_prefix|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"151348": {
|
156 |
+
"content": "<|code_middle|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"151349": {
|
164 |
+
"content": "<|code_suffix|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"151350": {
|
172 |
+
"content": "<think>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"151351": {
|
180 |
+
"content": "</think>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"151352": {
|
188 |
+
"content": "<tool_call>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"151353": {
|
196 |
+
"content": "</tool_call>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"151354": {
|
204 |
+
"content": "<tool_response>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"151355": {
|
212 |
+
"content": "</tool_response>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"151356": {
|
220 |
+
"content": "<arg_key>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"151357": {
|
228 |
+
"content": "</arg_key>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"151358": {
|
236 |
+
"content": "<arg_value>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"151359": {
|
244 |
+
"content": "</arg_value>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"151360": {
|
252 |
+
"content": "/nothink",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"151361": {
|
260 |
+
"content": "<|begin_of_box|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"151362": {
|
268 |
+
"content": "<|end_of_box|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"151363": {
|
276 |
+
"content": "<|image|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"151364": {
|
284 |
+
"content": "<|video|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
}
|
291 |
+
},
|
292 |
+
"additional_special_tokens": [
|
293 |
+
"<|endoftext|>",
|
294 |
+
"[MASK]",
|
295 |
+
"[gMASK]",
|
296 |
+
"[sMASK]",
|
297 |
+
"<sop>",
|
298 |
+
"<eop>",
|
299 |
+
"<|system|>",
|
300 |
+
"<|user|>",
|
301 |
+
"<|assistant|>",
|
302 |
+
"<|observation|>",
|
303 |
+
"<|begin_of_image|>",
|
304 |
+
"<|end_of_image|>",
|
305 |
+
"<|begin_of_video|>",
|
306 |
+
"<|end_of_video|>",
|
307 |
+
"<|begin_of_audio|>",
|
308 |
+
"<|end_of_audio|>",
|
309 |
+
"<|begin_of_transcription|>",
|
310 |
+
"<|end_of_transcription|>",
|
311 |
+
"<|code_prefix|>",
|
312 |
+
"<|code_middle|>",
|
313 |
+
"<|code_suffix|>",
|
314 |
+
"/nothink"
|
315 |
+
],
|
316 |
+
"clean_up_tokenization_spaces": false,
|
317 |
+
"do_lower_case": false,
|
318 |
+
"eos_token": "<|endoftext|>",
|
319 |
+
"extra_special_tokens": {},
|
320 |
+
"model_max_length": 128000,
|
321 |
+
"pad_token": "<|endoftext|>",
|
322 |
+
"padding_side": "left",
|
323 |
+
"remove_space": false,
|
324 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
325 |
+
}
|