Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- chat_template.jinja +103 -0
- config.json +74 -0
- generation_config.json +10 -0
- model-00001-of-00041.safetensors +3 -0
- model-00002-of-00041.safetensors +3 -0
- model-00003-of-00041.safetensors +3 -0
- model-00004-of-00041.safetensors +3 -0
- model-00005-of-00041.safetensors +3 -0
- model-00006-of-00041.safetensors +3 -0
- model-00007-of-00041.safetensors +3 -0
- model-00008-of-00041.safetensors +3 -0
- model-00009-of-00041.safetensors +3 -0
- model-00010-of-00041.safetensors +3 -0
- model-00011-of-00041.safetensors +3 -0
- model-00012-of-00041.safetensors +3 -0
- model-00013-of-00041.safetensors +3 -0
- model-00014-of-00041.safetensors +3 -0
- model-00015-of-00041.safetensors +3 -0
- model-00016-of-00041.safetensors +3 -0
- model-00017-of-00041.safetensors +3 -0
- model-00018-of-00041.safetensors +3 -0
- model-00019-of-00041.safetensors +3 -0
- model-00020-of-00041.safetensors +3 -0
- model-00021-of-00041.safetensors +3 -0
- model-00022-of-00041.safetensors +3 -0
- model-00023-of-00041.safetensors +3 -0
- model-00024-of-00041.safetensors +3 -0
- model-00025-of-00041.safetensors +3 -0
- model-00026-of-00041.safetensors +3 -0
- model-00027-of-00041.safetensors +3 -0
- model-00028-of-00041.safetensors +3 -0
- model-00029-of-00041.safetensors +3 -0
- model-00030-of-00041.safetensors +3 -0
- model-00031-of-00041.safetensors +3 -0
- model-00032-of-00041.safetensors +3 -0
- model-00033-of-00041.safetensors +3 -0
- model-00034-of-00041.safetensors +3 -0
- model-00035-of-00041.safetensors +3 -0
- model-00036-of-00041.safetensors +3 -0
- model-00037-of-00041.safetensors +3 -0
- model-00038-of-00041.safetensors +3 -0
- model-00039-of-00041.safetensors +3 -0
- model-00040-of-00041.safetensors +3 -0
- model-00041-of-00041.safetensors +3 -0
- model.safetensors.index.json +3 -0
- recipe.yaml +31 -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 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"input_activations": null,
|
36 |
+
"output_activations": null,
|
37 |
+
"targets": [
|
38 |
+
"Linear"
|
39 |
+
],
|
40 |
+
"weights": {
|
41 |
+
"actorder": null,
|
42 |
+
"block_structure": null,
|
43 |
+
"dynamic": false,
|
44 |
+
"group_size": 32,
|
45 |
+
"num_bits": 4,
|
46 |
+
"observer": "minmax",
|
47 |
+
"observer_kwargs": {},
|
48 |
+
"strategy": "group",
|
49 |
+
"symmetric": true,
|
50 |
+
"type": "int"
|
51 |
+
}
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"format": "pack-quantized",
|
55 |
+
"global_compression_ratio": null,
|
56 |
+
"ignore": [
|
57 |
+
"lm_head"
|
58 |
+
],
|
59 |
+
"kv_cache_scheme": null,
|
60 |
+
"quant_method": "compressed-tensors",
|
61 |
+
"quantization_status": "compressed"
|
62 |
+
},
|
63 |
+
"rms_norm_eps": 1e-05,
|
64 |
+
"rope_scaling": null,
|
65 |
+
"rope_theta": 1000000,
|
66 |
+
"routed_scaling_factor": 2.5,
|
67 |
+
"tie_word_embeddings": false,
|
68 |
+
"topk_group": 1,
|
69 |
+
"torch_dtype": "bfloat16",
|
70 |
+
"transformers_version": "4.56.0.dev0",
|
71 |
+
"use_cache": true,
|
72 |
+
"use_qk_norm": true,
|
73 |
+
"vocab_size": 151552
|
74 |
+
}
|
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-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ae923c5ffe114e459db689195c2e5d4833bc048d92a3037951c399e0a7b8b1
|
3 |
+
size 4998583992
|
model-00002-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a8ece13f98f5a14bef2f3c39058a96da06e2de338365bd909e17cb063da1c31
|
3 |
+
size 4996663472
|
model-00003-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4afa74b7bb439e5df6c50d865e1217d8b0565811440b106d9724cd40faec035
|
3 |
+
size 4996663744
|
model-00004-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6018a794d68d54d0e2eb56f2b748ad91b7403cd40d12125a5ead2b63a8c83802
|
3 |
+
size 4999824416
|
model-00005-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:028036709797a351e4cfd8fa815d65cc2fda35c8b709134ef967c46c6d2e53a8
|
3 |
+
size 4996666768
|
model-00006-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:872f954087ad36e0598b96809b9087958d0c5fe8b154f6502a40ba95051f8df4
|
3 |
+
size 4996666792
|
model-00007-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04413c371ee6fc22f6f8e16f48d0d4754b0742c25df3708c66eecf1455c7c9b5
|
3 |
+
size 4996667104
|
model-00008-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8437495b1806148baafaab71262735fa8c42106c8f37c8f6b54c8c4a19d5f893
|
3 |
+
size 4999826096
|
model-00009-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5775e2ce2dc9629bd89d89ec6d15e44048ba1ea6bba66f2696e77b6ba421b9ec
|
3 |
+
size 4996666792
|
model-00010-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8a74e72652bf3ab340cea1dedbd06f46c6c87028713e78712e687430a29e907
|
3 |
+
size 4996666792
|
model-00011-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e91a86903e75f3085b1447941b25bff690c197d84768d60e7cc21811ce083eaf
|
3 |
+
size 4996667144
|
model-00012-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:569b1933cf95ca498e6b05d1711580e5c21c7e769bfdb89a9d1c4f4b6154f0c6
|
3 |
+
size 4999826064
|
model-00013-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0527de25fe07533bf60551dc4acfd0724dd27e6f6662525c10e4b34b194b3fe
|
3 |
+
size 4996666792
|
model-00014-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d29a013608783a44f3b954ff842b9d744797d1a043b8ec573395d514c8f6069
|
3 |
+
size 4996666800
|
model-00015-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:298b3d60a9a54e462d83751bc97e6d33979a9c77a5965fdd621f1641a4945d9b
|
3 |
+
size 4996667176
|
model-00016-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a95274604787331504e1bca89d3616bfd640bfa2897abf479cd41775f3e3eafd
|
3 |
+
size 4999826024
|
model-00017-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f58d21962a57d63d6d54727dd6ac5a63ccb6dd48df26113da389b639bdbda89d
|
3 |
+
size 4996666792
|
model-00018-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36075d7fb9a9fd1505135922971ec189b57883a06a3fa5ed73b5fb3912426725
|
3 |
+
size 4996666832
|
model-00019-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0170c50d731bdd20db0095d4fc36fa736e354795bcb8c0d8fa2be503dee68c28
|
3 |
+
size 4996667176
|
model-00020-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37393ba2e3dad95a57b73ecdb012eae0db46d738ba5b987b17389423d2c57ae1
|
3 |
+
size 4999825992
|
model-00021-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9906bb5c55e949fa44a9b1095ba6ddbe464de97a68e4fab517333604ca20fbd0
|
3 |
+
size 4996666792
|
model-00022-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c20b4e77cba2310fb292e575a6e58ce5a74f76dab74a951a9e8df9237fae195
|
3 |
+
size 4996666872
|
model-00023-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da05aaaaa77f83472c11aa6bd9db3b1cd57774a3101f51abb9c96acdc87ac150
|
3 |
+
size 4996667176
|
model-00024-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4486df36f923312b489859cc00b2af98d32d54b95863f705f937cc4cb5a5fea
|
3 |
+
size 4999825952
|
model-00025-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ef1ae728dfdd2fb19973da08a0d5b3a9b7b418c1e48285d3ca21703a09dd5df
|
3 |
+
size 4996666792
|
model-00026-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc79c34be7908cf1ffa207d011da756f7f192fc1deeec5d1d21ce71c0fa5edaf
|
3 |
+
size 4996666904
|
model-00027-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84552243aad0a34200b595477392437676aa4988881b507fbbf872280da27eb8
|
3 |
+
size 4996667176
|
model-00028-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79bdf3cc3702563744cc0e1b99d574f6ede96ab88c6dce95d6ee48c6bc05f301
|
3 |
+
size 4999825920
|
model-00029-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10e6d58931b3f54ac80558d7e4895b54fa9577819852e35662a3bc12952b359e
|
3 |
+
size 4996666792
|
model-00030-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92380fe3582518bbdb38468b268452bc77fa96842f0834f798b5b1de7e4b3af7
|
3 |
+
size 4996666944
|
model-00031-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4822e18cf32665530858c1a100bd7877f1bf141a6019d36e22dde5e6d98fdc3e
|
3 |
+
size 4996667176
|
model-00032-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8e1cd2b08f44ce17b5f5d6ae1c668971215779d3df2c8b1cea6656624708a71
|
3 |
+
size 4999825880
|
model-00033-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b68fdaeb021b966c2c29509c531581792e1e328b77cb4e71489f592d2bbc01ad
|
3 |
+
size 4996666792
|
model-00034-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20c61013e7eac8c279b6e70c9380cb59956a8ad15e9b2e86466ba0f3b35654a4
|
3 |
+
size 4996666976
|
model-00035-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:540543e77f349c3ff8f22957f07ccb5e1727666eea45e01312a95e0933b44364
|
3 |
+
size 4971782736
|
model-00036-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e723944a00cdc41a818890918c67da94499a3a00536a2600dbd4a3ca8cf05832
|
3 |
+
size 4998165872
|
model-00037-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:489652dcbca31d421e3d93f48d742effb490f71a6f62d3ae93d7a9e252fa131d
|
3 |
+
size 4996666792
|
model-00038-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7958fd500cf58903f3fbbbf6964163cfd38649cc1a372ece6bdacf3afd8536f8
|
3 |
+
size 4996666992
|
model-00039-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c00d45b6b89cfa7b87bc82b3e07afdb9e0094d5c7650023fea957a163779f76
|
3 |
+
size 4986556096
|
model-00040-of-00041.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a569994e18dc9a1b8b0964bbb6899cdf3d3472fee6e1baea8b9862a8b1ec54
|
3 |
+
size 4389078424
|
model-00041-of-00041.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 sha256:2928626a4bf634e49f114fe515431e61ebaf2272a4282b5ebbf85c6ea7ee86e2
|
3 |
+
size 12668756
|
recipe.yaml
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_stage:
|
2 |
+
default_modifiers:
|
3 |
+
AWQModifier:
|
4 |
+
config_groups:
|
5 |
+
group_0:
|
6 |
+
targets: [Linear]
|
7 |
+
weights:
|
8 |
+
num_bits: 4
|
9 |
+
type: int
|
10 |
+
symmetric: true
|
11 |
+
group_size: 32
|
12 |
+
strategy: group
|
13 |
+
block_structure: null
|
14 |
+
dynamic: false
|
15 |
+
actorder: null
|
16 |
+
observer: minmax
|
17 |
+
observer_kwargs: {}
|
18 |
+
input_activations: null
|
19 |
+
output_activations: null
|
20 |
+
targets: [Linear]
|
21 |
+
ignore: [lm_head, 're:.*mlp.gate$']
|
22 |
+
mappings:
|
23 |
+
- smooth_layer: re:.*input_layernorm$
|
24 |
+
balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
|
25 |
+
- smooth_layer: re:.*v_proj$
|
26 |
+
balance_layers: ['re:.*o_proj$']
|
27 |
+
- smooth_layer: re:.*post_attention_layernorm$
|
28 |
+
balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
|
29 |
+
- smooth_layer: re:.*up_proj$
|
30 |
+
balance_layers: ['re:.*down_proj$']
|
31 |
+
duo_scaling: true
|
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
|
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 |
+
}
|