Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- chat_template.jinja +103 -0
- config.json +417 -0
- generation_config.json +10 -0
- model-00001-of-00047.safetensors +3 -0
- model-00002-of-00047.safetensors +3 -0
- model-00003-of-00047.safetensors +3 -0
- model-00004-of-00047.safetensors +3 -0
- model-00005-of-00047.safetensors +3 -0
- model-00006-of-00047.safetensors +3 -0
- model-00007-of-00047.safetensors +3 -0
- model-00008-of-00047.safetensors +3 -0
- model-00009-of-00047.safetensors +3 -0
- model-00010-of-00047.safetensors +3 -0
- model-00011-of-00047.safetensors +3 -0
- model-00012-of-00047.safetensors +3 -0
- model-00013-of-00047.safetensors +3 -0
- model-00014-of-00047.safetensors +3 -0
- model-00015-of-00047.safetensors +3 -0
- model-00016-of-00047.safetensors +3 -0
- model-00017-of-00047.safetensors +3 -0
- model-00018-of-00047.safetensors +3 -0
- model-00019-of-00047.safetensors +3 -0
- model-00020-of-00047.safetensors +3 -0
- model-00021-of-00047.safetensors +3 -0
- model-00022-of-00047.safetensors +3 -0
- model-00023-of-00047.safetensors +3 -0
- model-00024-of-00047.safetensors +3 -0
- model-00025-of-00047.safetensors +3 -0
- model-00026-of-00047.safetensors +3 -0
- model-00027-of-00047.safetensors +3 -0
- model-00028-of-00047.safetensors +3 -0
- model-00029-of-00047.safetensors +3 -0
- model-00030-of-00047.safetensors +3 -0
- model-00031-of-00047.safetensors +3 -0
- model-00032-of-00047.safetensors +3 -0
- model-00033-of-00047.safetensors +3 -0
- model-00034-of-00047.safetensors +3 -0
- model-00035-of-00047.safetensors +3 -0
- model-00036-of-00047.safetensors +3 -0
- model-00037-of-00047.safetensors +3 -0
- model-00038-of-00047.safetensors +3 -0
- model-00039-of-00047.safetensors +3 -0
- model-00041-of-00047.safetensors +3 -0
- model-00042-of-00047.safetensors +3 -0
- model-00043-of-00047.safetensors +3 -0
- model-00045-of-00047.safetensors +3 -0
- model-00047-of-00047.safetensors +3 -0
- model.safetensors.index.json +0 -0
- 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 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Glm4MoeForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": true,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"pad_token_id": 151329,
|
8 |
+
"eos_token_id": [
|
9 |
+
151329,
|
10 |
+
151336,
|
11 |
+
151338
|
12 |
+
],
|
13 |
+
"head_dim": 128,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 4096,
|
16 |
+
"partial_rotary_factor": 0.5,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 10944,
|
19 |
+
"max_position_embeddings": 131072,
|
20 |
+
"model_type": "glm4_moe",
|
21 |
+
"moe_intermediate_size": 1408,
|
22 |
+
"norm_topk_prob": true,
|
23 |
+
"num_attention_heads": 96,
|
24 |
+
"n_group": 1,
|
25 |
+
"topk_group": 1,
|
26 |
+
"n_routed_experts": 128,
|
27 |
+
"n_shared_experts": 1,
|
28 |
+
"routed_scaling_factor": 1.0,
|
29 |
+
"num_experts_per_tok": 8,
|
30 |
+
"first_k_dense_replace": 1,
|
31 |
+
"num_hidden_layers": 46,
|
32 |
+
"num_key_value_heads": 8,
|
33 |
+
"rms_norm_eps": 1e-05,
|
34 |
+
"rope_scaling": null,
|
35 |
+
"rope_theta": 1000000,
|
36 |
+
"num_nextn_predict_layers": 1,
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"torch_dtype": "bfloat16",
|
39 |
+
"transformers_version": "4.54.0",
|
40 |
+
"use_cache": true,
|
41 |
+
"use_qk_norm": false,
|
42 |
+
"vocab_size": 151552,
|
43 |
+
"quantization_config": {
|
44 |
+
"config_groups": {
|
45 |
+
"group_0": {
|
46 |
+
"input_activations": {
|
47 |
+
"actorder": null,
|
48 |
+
"block_structure": null,
|
49 |
+
"dynamic": true,
|
50 |
+
"group_size": null,
|
51 |
+
"num_bits": 8,
|
52 |
+
"observer": null,
|
53 |
+
"observer_kwargs": {},
|
54 |
+
"strategy": "token",
|
55 |
+
"symmetric": true,
|
56 |
+
"type": "float"
|
57 |
+
},
|
58 |
+
"output_activations": null,
|
59 |
+
"targets": [
|
60 |
+
"Linear"
|
61 |
+
],
|
62 |
+
"weights": {
|
63 |
+
"actorder": null,
|
64 |
+
"block_structure": null,
|
65 |
+
"dynamic": false,
|
66 |
+
"group_size": null,
|
67 |
+
"num_bits": 8,
|
68 |
+
"observer": "minmax",
|
69 |
+
"observer_kwargs": {},
|
70 |
+
"strategy": "channel",
|
71 |
+
"symmetric": true,
|
72 |
+
"type": "float"
|
73 |
+
}
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"format": "float-quantized",
|
77 |
+
"ignore": [
|
78 |
+
"model.layers.9.mlp.gate",
|
79 |
+
"model.layers.22.self_attn.q_proj.bias",
|
80 |
+
"model.layers.21.post_attention_layernorm",
|
81 |
+
"model.layers.46.post_attention_layernorm",
|
82 |
+
"model.layers.33.mlp.gate.e_score_correction_bias",
|
83 |
+
"model.layers.19.input_layernorm",
|
84 |
+
"model.layers.23.input_layernorm",
|
85 |
+
"model.layers.26.input_layernorm",
|
86 |
+
"model.layers.16.input_layernorm",
|
87 |
+
"model.layers.2.input_layernorm",
|
88 |
+
"model.layers.43.mlp.gate.e_score_correction_bias",
|
89 |
+
"model.layers.17.self_attn.v_proj.bias",
|
90 |
+
"model.layers.4.self_attn.k_proj.bias",
|
91 |
+
"model.layers.24.mlp.gate",
|
92 |
+
"model.layers.42.self_attn.q_proj.bias",
|
93 |
+
"model.layers.19.self_attn.v_proj.bias",
|
94 |
+
"model.layers.36.self_attn.k_proj.bias",
|
95 |
+
"model.layers.43.self_attn.k_proj.bias",
|
96 |
+
"model.layers.26.self_attn.v_proj.bias",
|
97 |
+
"model.layers.33.mlp.gate",
|
98 |
+
"model.layers.31.input_layernorm",
|
99 |
+
"model.layers.8.input_layernorm",
|
100 |
+
"model.layers.9.mlp.gate.e_score_correction_bias",
|
101 |
+
"model.layers.19.mlp.gate.e_score_correction_bias",
|
102 |
+
"model.layers.14.self_attn.v_proj.bias",
|
103 |
+
"model.layers.19.mlp.gate",
|
104 |
+
"model.layers.12.mlp.gate",
|
105 |
+
"model.layers.37.mlp.gate.e_score_correction_bias",
|
106 |
+
"model.layers.39.mlp.gate",
|
107 |
+
"model.layers.20.self_attn.v_proj.bias",
|
108 |
+
"model.layers.1.self_attn.q_proj.bias",
|
109 |
+
"model.layers.7.self_attn.k_proj.bias",
|
110 |
+
"model.layers.19.self_attn.k_proj.bias",
|
111 |
+
"model.layers.30.mlp.gate.e_score_correction_bias",
|
112 |
+
"model.layers.37.input_layernorm",
|
113 |
+
"model.layers.40.self_attn.q_proj.bias",
|
114 |
+
"model.layers.30.input_layernorm",
|
115 |
+
"model.layers.10.post_attention_layernorm",
|
116 |
+
"model.layers.10.mlp.gate",
|
117 |
+
"model.layers.21.mlp.gate",
|
118 |
+
"model.layers.39.post_attention_layernorm",
|
119 |
+
"model.layers.20.self_attn.q_proj.bias",
|
120 |
+
"model.layers.20.input_layernorm",
|
121 |
+
"model.layers.16.self_attn.v_proj.bias",
|
122 |
+
"model.layers.5.self_attn.k_proj.bias",
|
123 |
+
"model.layers.18.input_layernorm",
|
124 |
+
"model.layers.35.input_layernorm",
|
125 |
+
"model.layers.43.mlp.gate",
|
126 |
+
"model.layers.5.self_attn.v_proj.bias",
|
127 |
+
"model.layers.28.mlp.gate",
|
128 |
+
"model.layers.4.self_attn.v_proj.bias",
|
129 |
+
"model.layers.46.mlp.gate.e_score_correction_bias",
|
130 |
+
"model.layers.25.mlp.gate.e_score_correction_bias",
|
131 |
+
"model.layers.46.enorm",
|
132 |
+
"model.layers.30.self_attn.k_proj.bias",
|
133 |
+
"model.layers.27.self_attn.v_proj.bias",
|
134 |
+
"model.layers.23.mlp.gate",
|
135 |
+
"model.layers.38.post_attention_layernorm",
|
136 |
+
"model.layers.0.post_attention_layernorm",
|
137 |
+
"model.layers.46.self_attn.k_proj.bias",
|
138 |
+
"model.layers.26.post_attention_layernorm",
|
139 |
+
"model.layers.26.self_attn.q_proj.bias",
|
140 |
+
"model.layers.46.embed_tokens",
|
141 |
+
"model.layers.24.input_layernorm",
|
142 |
+
"model.layers.41.post_attention_layernorm",
|
143 |
+
"model.layers.20.mlp.gate",
|
144 |
+
"model.layers.3.mlp.gate",
|
145 |
+
"model.layers.22.input_layernorm",
|
146 |
+
"model.layers.15.post_attention_layernorm",
|
147 |
+
"model.layers.39.input_layernorm",
|
148 |
+
"model.layers.42.mlp.gate.e_score_correction_bias",
|
149 |
+
"model.layers.34.mlp.gate",
|
150 |
+
"model.layers.13.mlp.gate",
|
151 |
+
"model.layers.38.input_layernorm",
|
152 |
+
"model.layers.15.self_attn.q_proj.bias",
|
153 |
+
"model.layers.7.post_attention_layernorm",
|
154 |
+
"model.layers.28.self_attn.v_proj.bias",
|
155 |
+
"model.layers.36.post_attention_layernorm",
|
156 |
+
"model.layers.34.self_attn.k_proj.bias",
|
157 |
+
"model.layers.23.post_attention_layernorm",
|
158 |
+
"model.layers.43.input_layernorm",
|
159 |
+
"model.layers.39.self_attn.k_proj.bias",
|
160 |
+
"model.layers.18.post_attention_layernorm",
|
161 |
+
"model.layers.29.mlp.gate.e_score_correction_bias",
|
162 |
+
"model.layers.34.mlp.gate.e_score_correction_bias",
|
163 |
+
"model.layers.28.self_attn.q_proj.bias",
|
164 |
+
"model.layers.46.eh_proj",
|
165 |
+
"model.layers.14.mlp.gate.e_score_correction_bias",
|
166 |
+
"model.layers.7.mlp.gate.e_score_correction_bias",
|
167 |
+
"model.layers.35.self_attn.k_proj.bias",
|
168 |
+
"model.layers.13.post_attention_layernorm",
|
169 |
+
"model.layers.22.self_attn.k_proj.bias",
|
170 |
+
"model.layers.4.self_attn.q_proj.bias",
|
171 |
+
"model.layers.41.self_attn.k_proj.bias",
|
172 |
+
"model.layers.12.post_attention_layernorm",
|
173 |
+
"model.layers.37.self_attn.q_proj.bias",
|
174 |
+
"model.layers.46.input_layernorm",
|
175 |
+
"model.layers.24.self_attn.k_proj.bias",
|
176 |
+
"model.layers.5.mlp.gate",
|
177 |
+
"model.layers.9.self_attn.k_proj.bias",
|
178 |
+
"model.layers.10.self_attn.v_proj.bias",
|
179 |
+
"model.layers.42.self_attn.v_proj.bias",
|
180 |
+
"model.embed_tokens",
|
181 |
+
"model.layers.2.self_attn.q_proj.bias",
|
182 |
+
"model.layers.28.mlp.gate.e_score_correction_bias",
|
183 |
+
"model.layers.24.self_attn.v_proj.bias",
|
184 |
+
"model.layers.15.input_layernorm",
|
185 |
+
"model.layers.9.input_layernorm",
|
186 |
+
"model.layers.33.input_layernorm",
|
187 |
+
"model.layers.45.self_attn.v_proj.bias",
|
188 |
+
"model.layers.31.self_attn.q_proj.bias",
|
189 |
+
"model.layers.34.input_layernorm",
|
190 |
+
"model.layers.14.input_layernorm",
|
191 |
+
"model.layers.17.post_attention_layernorm",
|
192 |
+
"model.layers.0.self_attn.k_proj.bias",
|
193 |
+
"model.layers.37.self_attn.v_proj.bias",
|
194 |
+
"model.norm",
|
195 |
+
"model.layers.9.self_attn.q_proj.bias",
|
196 |
+
"model.layers.4.input_layernorm",
|
197 |
+
"model.layers.45.self_attn.q_proj.bias",
|
198 |
+
"model.layers.7.self_attn.q_proj.bias",
|
199 |
+
"model.layers.32.self_attn.v_proj.bias",
|
200 |
+
"model.layers.22.self_attn.v_proj.bias",
|
201 |
+
"model.layers.45.post_attention_layernorm",
|
202 |
+
"model.layers.40.mlp.gate",
|
203 |
+
"model.layers.29.self_attn.v_proj.bias",
|
204 |
+
"model.layers.3.mlp.gate.e_score_correction_bias",
|
205 |
+
"model.layers.31.post_attention_layernorm",
|
206 |
+
"model.layers.41.self_attn.v_proj.bias",
|
207 |
+
"model.layers.5.input_layernorm",
|
208 |
+
"model.layers.13.self_attn.v_proj.bias",
|
209 |
+
"model.layers.26.self_attn.k_proj.bias",
|
210 |
+
"model.layers.28.post_attention_layernorm",
|
211 |
+
"model.layers.17.mlp.gate",
|
212 |
+
"model.layers.42.mlp.gate",
|
213 |
+
"model.layers.34.self_attn.v_proj.bias",
|
214 |
+
"model.layers.1.mlp.gate.e_score_correction_bias",
|
215 |
+
"model.layers.21.input_layernorm",
|
216 |
+
"model.layers.21.self_attn.k_proj.bias",
|
217 |
+
"model.layers.29.self_attn.k_proj.bias",
|
218 |
+
"model.layers.20.post_attention_layernorm",
|
219 |
+
"model.layers.14.post_attention_layernorm",
|
220 |
+
"model.layers.34.post_attention_layernorm",
|
221 |
+
"model.layers.27.self_attn.k_proj.bias",
|
222 |
+
"model.layers.24.mlp.gate.e_score_correction_bias",
|
223 |
+
"model.layers.31.mlp.gate.e_score_correction_bias",
|
224 |
+
"model.layers.2.self_attn.k_proj.bias",
|
225 |
+
"model.layers.25.self_attn.v_proj.bias",
|
226 |
+
"model.layers.1.post_attention_layernorm",
|
227 |
+
"model.layers.10.self_attn.q_proj.bias",
|
228 |
+
"model.layers.16.mlp.gate.e_score_correction_bias",
|
229 |
+
"model.layers.16.self_attn.q_proj.bias",
|
230 |
+
"model.layers.38.mlp.gate.e_score_correction_bias",
|
231 |
+
"model.layers.46.self_attn.q_proj.bias",
|
232 |
+
"model.layers.23.self_attn.k_proj.bias",
|
233 |
+
"model.layers.42.post_attention_layernorm",
|
234 |
+
"model.layers.33.self_attn.k_proj.bias",
|
235 |
+
"model.layers.30.mlp.gate",
|
236 |
+
"model.layers.34.self_attn.q_proj.bias",
|
237 |
+
"model.layers.4.post_attention_layernorm",
|
238 |
+
"model.layers.13.self_attn.k_proj.bias",
|
239 |
+
"model.layers.2.post_attention_layernorm",
|
240 |
+
"model.layers.40.post_attention_layernorm",
|
241 |
+
"model.layers.38.self_attn.k_proj.bias",
|
242 |
+
"model.layers.1.self_attn.k_proj.bias",
|
243 |
+
"model.layers.10.mlp.gate.e_score_correction_bias",
|
244 |
+
"model.layers.43.self_attn.v_proj.bias",
|
245 |
+
"model.layers.11.input_layernorm",
|
246 |
+
"model.layers.42.input_layernorm",
|
247 |
+
"model.layers.19.self_attn.q_proj.bias",
|
248 |
+
"model.layers.24.post_attention_layernorm",
|
249 |
+
"model.layers.12.input_layernorm",
|
250 |
+
"model.layers.42.self_attn.k_proj.bias",
|
251 |
+
"model.layers.12.self_attn.k_proj.bias",
|
252 |
+
"model.layers.0.self_attn.v_proj.bias",
|
253 |
+
"model.layers.1.mlp.gate",
|
254 |
+
"model.layers.39.self_attn.v_proj.bias",
|
255 |
+
"model.layers.14.mlp.gate",
|
256 |
+
"model.layers.44.post_attention_layernorm",
|
257 |
+
"model.layers.37.mlp.gate",
|
258 |
+
"model.layers.31.mlp.gate",
|
259 |
+
"model.layers.8.post_attention_layernorm",
|
260 |
+
"model.layers.2.mlp.gate.e_score_correction_bias",
|
261 |
+
"model.layers.36.input_layernorm",
|
262 |
+
"model.layers.30.post_attention_layernorm",
|
263 |
+
"model.layers.46.shared_head.norm",
|
264 |
+
"model.layers.4.mlp.gate",
|
265 |
+
"model.layers.6.mlp.gate",
|
266 |
+
"model.layers.29.mlp.gate",
|
267 |
+
"model.layers.7.mlp.gate",
|
268 |
+
"model.layers.0.self_attn.q_proj.bias",
|
269 |
+
"model.layers.44.mlp.gate",
|
270 |
+
"model.layers.32.self_attn.k_proj.bias",
|
271 |
+
"model.layers.4.mlp.gate.e_score_correction_bias",
|
272 |
+
"model.layers.18.self_attn.v_proj.bias",
|
273 |
+
"model.layers.30.self_attn.q_proj.bias",
|
274 |
+
"model.layers.21.mlp.gate.e_score_correction_bias",
|
275 |
+
"model.layers.32.post_attention_layernorm",
|
276 |
+
"model.layers.19.post_attention_layernorm",
|
277 |
+
"model.layers.22.mlp.gate",
|
278 |
+
"model.layers.13.mlp.gate.e_score_correction_bias",
|
279 |
+
"model.layers.8.mlp.gate",
|
280 |
+
"model.layers.36.self_attn.v_proj.bias",
|
281 |
+
"model.layers.5.post_attention_layernorm",
|
282 |
+
"model.layers.32.input_layernorm",
|
283 |
+
"model.layers.33.post_attention_layernorm",
|
284 |
+
"model.layers.21.self_attn.v_proj.bias",
|
285 |
+
"model.layers.2.mlp.gate",
|
286 |
+
"model.layers.13.input_layernorm",
|
287 |
+
"model.layers.15.self_attn.v_proj.bias",
|
288 |
+
"model.layers.16.self_attn.k_proj.bias",
|
289 |
+
"model.layers.2.self_attn.v_proj.bias",
|
290 |
+
"model.layers.43.post_attention_layernorm",
|
291 |
+
"model.layers.7.input_layernorm",
|
292 |
+
"model.layers.29.post_attention_layernorm",
|
293 |
+
"model.layers.20.self_attn.k_proj.bias",
|
294 |
+
"model.layers.38.mlp.gate",
|
295 |
+
"model.layers.18.mlp.gate.e_score_correction_bias",
|
296 |
+
"model.layers.25.input_layernorm",
|
297 |
+
"model.layers.1.input_layernorm",
|
298 |
+
"model.layers.46.hnorm",
|
299 |
+
"model.layers.31.self_attn.v_proj.bias",
|
300 |
+
"model.layers.14.self_attn.q_proj.bias",
|
301 |
+
"model.layers.18.self_attn.q_proj.bias",
|
302 |
+
"model.layers.8.self_attn.q_proj.bias",
|
303 |
+
"model.layers.35.self_attn.v_proj.bias",
|
304 |
+
"model.layers.45.mlp.gate.e_score_correction_bias",
|
305 |
+
"model.layers.9.post_attention_layernorm",
|
306 |
+
"model.layers.30.self_attn.v_proj.bias",
|
307 |
+
"model.layers.15.mlp.gate",
|
308 |
+
"model.layers.10.input_layernorm",
|
309 |
+
"model.layers.6.self_attn.q_proj.bias",
|
310 |
+
"model.layers.11.mlp.gate.e_score_correction_bias",
|
311 |
+
"model.layers.41.input_layernorm",
|
312 |
+
"model.layers.22.mlp.gate.e_score_correction_bias",
|
313 |
+
"model.layers.15.mlp.gate.e_score_correction_bias",
|
314 |
+
"model.layers.21.self_attn.q_proj.bias",
|
315 |
+
"model.layers.17.mlp.gate.e_score_correction_bias",
|
316 |
+
"model.layers.16.mlp.gate",
|
317 |
+
"model.layers.25.self_attn.q_proj.bias",
|
318 |
+
"model.layers.6.input_layernorm",
|
319 |
+
"model.layers.17.input_layernorm",
|
320 |
+
"model.layers.26.mlp.gate.e_score_correction_bias",
|
321 |
+
"model.layers.35.mlp.gate.e_score_correction_bias",
|
322 |
+
"model.layers.0.input_layernorm",
|
323 |
+
"model.layers.3.post_attention_layernorm",
|
324 |
+
"model.layers.6.self_attn.v_proj.bias",
|
325 |
+
"model.layers.27.mlp.gate.e_score_correction_bias",
|
326 |
+
"model.layers.18.mlp.gate",
|
327 |
+
"model.layers.28.input_layernorm",
|
328 |
+
"model.layers.9.self_attn.v_proj.bias",
|
329 |
+
"model.layers.31.self_attn.k_proj.bias",
|
330 |
+
"model.layers.40.self_attn.v_proj.bias",
|
331 |
+
"model.layers.12.self_attn.q_proj.bias",
|
332 |
+
"model.layers.41.mlp.gate",
|
333 |
+
"model.layers.5.self_attn.q_proj.bias",
|
334 |
+
"model.layers.11.self_attn.v_proj.bias",
|
335 |
+
"model.layers.36.mlp.gate",
|
336 |
+
"model.layers.27.self_attn.q_proj.bias",
|
337 |
+
"model.layers.40.self_attn.k_proj.bias",
|
338 |
+
"model.layers.11.post_attention_layernorm",
|
339 |
+
"model.layers.27.input_layernorm",
|
340 |
+
"model.layers.12.self_attn.v_proj.bias",
|
341 |
+
"model.layers.46.mlp.gate",
|
342 |
+
"model.layers.17.self_attn.k_proj.bias",
|
343 |
+
"model.layers.3.input_layernorm",
|
344 |
+
"model.layers.44.input_layernorm",
|
345 |
+
"model.layers.10.self_attn.k_proj.bias",
|
346 |
+
"model.layers.41.mlp.gate.e_score_correction_bias",
|
347 |
+
"model.layers.7.self_attn.v_proj.bias",
|
348 |
+
"model.layers.18.self_attn.k_proj.bias",
|
349 |
+
"model.layers.1.self_attn.v_proj.bias",
|
350 |
+
"model.layers.26.mlp.gate",
|
351 |
+
"model.layers.45.input_layernorm",
|
352 |
+
"model.layers.23.self_attn.v_proj.bias",
|
353 |
+
"model.layers.39.mlp.gate.e_score_correction_bias",
|
354 |
+
"model.layers.12.mlp.gate.e_score_correction_bias",
|
355 |
+
"model.layers.37.post_attention_layernorm",
|
356 |
+
"model.layers.46.self_attn.v_proj.bias",
|
357 |
+
"model.layers.36.mlp.gate.e_score_correction_bias",
|
358 |
+
"model.layers.5.mlp.gate.e_score_correction_bias",
|
359 |
+
"model.layers.35.mlp.gate",
|
360 |
+
"model.layers.44.self_attn.k_proj.bias",
|
361 |
+
"model.layers.3.self_attn.k_proj.bias",
|
362 |
+
"model.layers.11.mlp.gate",
|
363 |
+
"model.layers.11.self_attn.q_proj.bias",
|
364 |
+
"model.layers.17.self_attn.q_proj.bias",
|
365 |
+
"model.layers.32.self_attn.q_proj.bias",
|
366 |
+
"model.layers.11.self_attn.k_proj.bias",
|
367 |
+
"model.layers.40.mlp.gate.e_score_correction_bias",
|
368 |
+
"model.layers.41.self_attn.q_proj.bias",
|
369 |
+
"model.layers.15.self_attn.k_proj.bias",
|
370 |
+
"model.layers.44.self_attn.v_proj.bias",
|
371 |
+
"model.layers.25.self_attn.k_proj.bias",
|
372 |
+
"model.layers.25.post_attention_layernorm",
|
373 |
+
"model.layers.29.input_layernorm",
|
374 |
+
"model.layers.44.self_attn.q_proj.bias",
|
375 |
+
"model.layers.16.post_attention_layernorm",
|
376 |
+
"model.layers.6.mlp.gate.e_score_correction_bias",
|
377 |
+
"model.layers.38.self_attn.v_proj.bias",
|
378 |
+
"model.layers.40.input_layernorm",
|
379 |
+
"model.layers.6.post_attention_layernorm",
|
380 |
+
"model.layers.22.post_attention_layernorm",
|
381 |
+
"model.layers.8.self_attn.k_proj.bias",
|
382 |
+
"model.layers.37.self_attn.k_proj.bias",
|
383 |
+
"model.layers.23.mlp.gate.e_score_correction_bias",
|
384 |
+
"model.layers.27.mlp.gate",
|
385 |
+
"model.layers.8.mlp.gate.e_score_correction_bias",
|
386 |
+
"model.layers.28.self_attn.k_proj.bias",
|
387 |
+
"model.layers.24.self_attn.q_proj.bias",
|
388 |
+
"model.layers.39.self_attn.q_proj.bias",
|
389 |
+
"model.layers.36.self_attn.q_proj.bias",
|
390 |
+
"model.layers.45.self_attn.k_proj.bias",
|
391 |
+
"model.layers.32.mlp.gate.e_score_correction_bias",
|
392 |
+
"model.layers.35.self_attn.q_proj.bias",
|
393 |
+
"model.layers.33.self_attn.q_proj.bias",
|
394 |
+
"model.layers.14.self_attn.k_proj.bias",
|
395 |
+
"lm_head",
|
396 |
+
"model.layers.3.self_attn.v_proj.bias",
|
397 |
+
"model.layers.44.mlp.gate.e_score_correction_bias",
|
398 |
+
"model.layers.45.mlp.gate",
|
399 |
+
"model.layers.32.mlp.gate",
|
400 |
+
"model.layers.33.self_attn.v_proj.bias",
|
401 |
+
"model.layers.29.self_attn.q_proj.bias",
|
402 |
+
"model.layers.3.self_attn.q_proj.bias",
|
403 |
+
"model.layers.35.post_attention_layernorm",
|
404 |
+
"model.layers.6.self_attn.k_proj.bias",
|
405 |
+
"model.layers.43.self_attn.q_proj.bias",
|
406 |
+
"model.layers.20.mlp.gate.e_score_correction_bias",
|
407 |
+
"model.layers.8.self_attn.v_proj.bias",
|
408 |
+
"model.layers.13.self_attn.q_proj.bias",
|
409 |
+
"model.layers.27.post_attention_layernorm",
|
410 |
+
"model.layers.38.self_attn.q_proj.bias",
|
411 |
+
"model.layers.25.mlp.gate",
|
412 |
+
"model.layers.23.self_attn.q_proj.bias"
|
413 |
+
],
|
414 |
+
"quant_method": "compressed-tensors",
|
415 |
+
"quantization_status": "compressed"
|
416 |
+
}
|
417 |
+
}
|
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": "4.54.0"
|
10 |
+
}
|
model-00001-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a402a8fac66c090eddd032e70aaa5ab9c87307aa44451c659e1b650f9c60ad53
|
3 |
+
size 2726784880
|
model-00002-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d3801d622ff4292be51939389c2e30aac77dfc0d6728d777077b1d892c8eb7f
|
3 |
+
size 2345777464
|
model-00003-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:370acfd3919de83ddde52b13520200c889233d776546a9b8f6834ce09163af72
|
3 |
+
size 2345777464
|
model-00004-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ee5f8494b76e349c0065073df819272b4abf799a56815ac0faa216251cd9075
|
3 |
+
size 2345777464
|
model-00005-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc1fe9b9550617ee72997b29fc8f13d391a7bb1439d1df1d5ba5c159bcd5c78
|
3 |
+
size 2345777464
|
model-00006-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee91fb563f9d471d1870f99496bbe576dd7435127d506cd251d8a40a0581ea25
|
3 |
+
size 2345777464
|
model-00007-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56b80408c45881d8b1aa234ebe4c4826af24abc26038051cd92ce0aa2212070
|
3 |
+
size 2345777464
|
model-00008-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f78687be00665850826872a5666ac3fb72c15cb70ffb6f8ab7da2e402ddfa307
|
3 |
+
size 2345777464
|
model-00009-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65c39636822e6fa307ca0e27c4cc14e8045a80799f801d638a1ef6138534db37
|
3 |
+
size 2345777464
|
model-00010-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dd40942500a67c1c7f3eee752a6777876923eea9b00fe3abe898794f5b44e28
|
3 |
+
size 2345777464
|
model-00011-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e400a5ca71912ac0ca8da5fc103c0ee6a7dd25eb68816620b4f30eb48e30138c
|
3 |
+
size 2345778256
|
model-00012-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8b28bbe7d35824f3fcd79833333c1427dd844f9fa5872fb9b4e237a4b923e9
|
3 |
+
size 2345778256
|
model-00013-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b08854bbbeebd8df2cca69c83036698950b0ab0aca37497d4db5af1da55e021
|
3 |
+
size 2345778256
|
model-00014-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97df7e09418afdbeb89677b8baa1a8456a45c70f92597f307ea710c7fc71e5b5
|
3 |
+
size 2345778256
|
model-00015-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb3cd4497d95e3fc0d679a3344d7bcf8ef50bcf9074eed34b5596099e6061624
|
3 |
+
size 2345778256
|
model-00016-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9e55954e25fda8f2b1c224a39e2350ed29595659786ed9db1fdf30b03623ba9
|
3 |
+
size 2345778256
|
model-00017-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdda21d70b7bf6e067a7da0b9abfbde5d7fbb33740fa0b4d2839b316f61f2f69
|
3 |
+
size 2345778256
|
model-00018-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:235e3a593ac9bccd5e6ee9ba1d8d5539c78b30632dafa2ce39ede0a6e7ce8a5f
|
3 |
+
size 2345778256
|
model-00019-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75fe5acbcb61b0c243f52d7e2a3436f73c4b41f2b7645779d7f092cac8d6c122
|
3 |
+
size 2345778256
|
model-00020-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e68c695f2d732a714c09ab07832dca8443ddcdc745bc4fc19c49962a1ff69a79
|
3 |
+
size 2345778256
|
model-00021-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bcd058b41a7fef9d6c05cb024e776ee78f7cd00cf8c73b5e912fc28e32e7454
|
3 |
+
size 2345778256
|
model-00022-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31225cc96950af59d7775e287a7af7ffdf2a13ce8073114cef082a06e5c58083
|
3 |
+
size 2345778256
|
model-00023-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d71c2b109c55b79c61e98af7b80148a91a008770de217fee16483ec9f1eb8eef
|
3 |
+
size 2345778256
|
model-00024-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6077ad7f4ef58045de15cb4bdf66ca773d9917eb8179f1b5160ed65931be07cf
|
3 |
+
size 2345778256
|
model-00025-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fa816ebe9f85d1a21c26182a4f2620b090604066136e2dee997d7c16c62e845
|
3 |
+
size 2345778256
|
model-00026-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ede66e0f34d047a685d0c88d4392b2ea7320c1f9ec58a91cdf86a3aa3187c111
|
3 |
+
size 2345778256
|
model-00027-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae3404cd91efa7632e7761cef0e36d287531043b8293e8ca231f80556de0c943
|
3 |
+
size 2345778256
|
model-00028-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc866b2ceb0c216a0e34f0a5d7d7178e28db4f1170778ea2ee813c487adad690
|
3 |
+
size 2345778256
|
model-00029-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86c0aeefe2ccf3db32de08f211c89b2dac92f08ab9fce79a9cd0dac3a7168c94
|
3 |
+
size 2345778256
|
model-00030-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:934d52a70fce1b5350a6097a60b6e7d56e5c62e74bbd1f978b06b2cb05eda181
|
3 |
+
size 2345778256
|
model-00031-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1ae794e253939c3ace1438e156ee049c8380294a7cf2ceb71df6d24f3db7529
|
3 |
+
size 2345778256
|
model-00032-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be9c3a1a94eb73278eee04f20536984049a19d22cfec99842f130f9a0124b679
|
3 |
+
size 2345778256
|
model-00033-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fe977ee1930c5371511e72358fe28b6652153c144682f0d0b25985396a2d9f3
|
3 |
+
size 2345778256
|
model-00034-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56e8edad38c7825a51eb2d95e696779b126571861a23570d3c830d5145af88d5
|
3 |
+
size 2345778256
|
model-00035-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1987ca16a5051008d42528a6090e0858cca95e96635c17630fc4b42be64fba2b
|
3 |
+
size 2345778256
|
model-00036-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d96fd512b5e06a9ba547a9075c0c92ed87d48f58bd55e70cd1d36ab370e953d
|
3 |
+
size 2345778256
|
model-00037-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:043d5e8e4fce151634a4bcb8a06a782eacd12cbe10617c4e6dad70036040b6d6
|
3 |
+
size 2345778256
|
model-00038-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abd38bbfa42f52515791133a1f613fdb59bfbc7c36eb5494c56367545c025df8
|
3 |
+
size 2345778256
|
model-00039-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9d9984281c5587e6749846705853d14287a6bf13ac4f55cc8eb45db25d85123
|
3 |
+
size 2345778256
|
model-00041-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc0dbeba62a43bc2bb5420e32c2fbbd0b246f3422210c45338a34567f814e166
|
3 |
+
size 2345778256
|
model-00042-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:140b23ed6313b17d3bb83dfa408489f416e2b4fb69ab213a0fa95cdaa9266022
|
3 |
+
size 2345778256
|
model-00043-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:405cc1ce09cb6f98b93465847c673266b6e2769322929cb7a89a4bad1f23995f
|
3 |
+
size 2345778256
|
model-00045-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:660f9a5d8ce0fc3c6bb06dadbe7ef096737a56583222f127219185d6636490c9
|
3 |
+
size 2345778256
|
model-00047-of-00047.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e40754924a9ee2229bd1f5ec0a2191a831f6dbf9f9d6f5ef534c6a2a1e8f7cb
|
3 |
+
size 2412912168
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd
|
3 |
+
size 19970699
|