audio-cpp commited on
Commit
a9e125e
·
verified ·
1 Parent(s): 199a4a1

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,9 +33,16 @@ 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
36
- Irodori-TTS-500M-v3-GGUF/irodori-tts-500m-v3-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
- Irodori-TTS-500M-v3-GGUF/irodori-tts-500m-v3-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
38
- Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-f16.gguf filter=lfs diff=lfs merge=lfs -text
39
- Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
- Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-f16.gguf filter=lfs diff=lfs merge=lfs -text
41
- Irodori-TTS-v4-Small-GGUF/irodori-tts-v4-small-q8_0.gguf 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
+ DotTTS-MF-GGUF/dots-tts-mf-bf16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ DotTTS-MF-GGUF/dots-tts-mf-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
38
+ DotTTS-SOAR-GGUF/dots-tts-soar-bf16.gguf filter=lfs diff=lfs merge=lfs -text
39
+ DotTTS-SOAR-GGUF/dots-tts-soar-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ MiniMax-H3-Q4-GGUF/audio_vae.gguf filter=lfs diff=lfs merge=lfs -text
41
+ MiniMax-H3-Q4-GGUF/audio_vae_folded_f16.gguf filter=lfs diff=lfs merge=lfs -text
42
+ MiniMax-H3-Q4-GGUF/dit.gguf filter=lfs diff=lfs merge=lfs -text
43
+ MiniMax-H3-Q4-GGUF/text_encoder_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
44
+ MiniMax-H3-Q4-GGUF/video_vae.gguf filter=lfs diff=lfs merge=lfs -text
45
+ MuScriptor-Small-GGUF/muscriptor-small-f32.gguf filter=lfs diff=lfs merge=lfs -text
46
+ NeuTTS-2E-GGUF/neutts-2e-orig.gguf filter=lfs diff=lfs merge=lfs -text
47
+ PersonaPlex-GGUF/personaplex-7b-v1-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
48
+ PersonaPlex-GGUF/personaplex-7b-v1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DotTTS-MF-GGUF/dots-tts-mf-bf16.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:384de4f8583943467f71abc3af1502656fd3841eb70cc6745f9416fe11421214
3
- size 4791410080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedfa0415229fbb5d0b59ab4fe0327513720bacfc3f7705cca3c2d6315f911af
3
+ size 4791356672
DotTTS-MF-GGUF/dots-tts-mf-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062c5e040e0ec9a2d31dc1209d70233ed2bb132e9ead5cea84af420644079053
3
+ size 2965375840
DotTTS-SOAR-GGUF/dots-tts-soar-bf16.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5292089b053ffa55dddaa3eb5e888c7adefee75006f8d0e6c717a13c4933a41c
3
- size 4788783360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77cc9e0881d50064990dba19b01e7faec8610b5ba2fdf563a86699006fb7a51
3
+ size 4788730464
DotTTS-SOAR-GGUF/dots-tts-soar-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0633a6b4b705accee3858ffb129f403dc5aa64e634a80f713f4bde6f002fc2f0
3
+ size 2962749632
MiniMax-H3-Q4-GGUF/FL2VA/processor/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
3
+ }
MiniMax-H3-Q4-GGUF/FL2VA/processor/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
MiniMax-H3-Q4-GGUF/FL2VA/processor/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
MiniMax-H3-Q4-GGUF/FL2VA/processor/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
MiniMax-H3-Q4-GGUF/FL2VA/processor/tokenizer_config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>",
228
+ "<d>",
229
+ "</d>",
230
+ "<|cutoff|>",
231
+ "<|lyrics_start|>",
232
+ "<|lyrics_end|>",
233
+ "<|caption_start|>",
234
+ "<|caption_end|>"
235
+ ],
236
+ "bos_token": null,
237
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
238
+ "clean_up_tokenization_spaces": false,
239
+ "eos_token": "<|im_end|>",
240
+ "errors": "replace",
241
+ "model_max_length": 262144,
242
+ "pad_token": "<|endoftext|>",
243
+ "split_special_tokens": false,
244
+ "tokenizer_class": "Qwen2Tokenizer",
245
+ "unk_token": null
246
+ }
MiniMax-H3-Q4-GGUF/FL2VA/processor/video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
MiniMax-H3-Q4-GGUF/FL2VA/processor/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
MiniMax-H3-Q4-GGUF/audio_vae.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b24bff24fd5e2ff97cb9ec6a8353bde90b5baeeb4df465d0847c54b93725cad
3
+ size 296126496
MiniMax-H3-Q4-GGUF/audio_vae_folded_f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7ddc1acb542d5168bf0944890f27f57e32b46e1c7f5918b0ca35a7e85bca05
3
+ size 284562816
MiniMax-H3-Q4-GGUF/configuration.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"task":"text-to-video-synthesis"}
MiniMax-H3-Q4-GGUF/dit.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f122a03b9e04a837889504a6612e7d4acbfa85ac648405726b8e49e5fbdadd0c
3
+ size 15502530720
MiniMax-H3-Q4-GGUF/text_encoder_q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82985a5b59d83ab20cd5ba66195a1af380d9b66c76211e3bda9292a95830e55b
3
+ size 15270376000
MiniMax-H3-Q4-GGUF/video_vae.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e98a348d9d9357af7b32625a4bc43e7df85aab4236b1ba14635f8d724c27e24
3
+ size 1374245472
MuScriptor-Small-GGUF/muscriptor-small-f32.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bff6f1c45b445e144c176434fbe27614ad6c4686e03f99ee11b17e15163fba2
3
+ size 411908672
NeuTTS-2E-GGUF/neutts-2e-orig.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1b437f6ae9ba005930a38977573f994bc08290f3b16ee6ca99028a2aeb402d
3
+ size 3016181288
PersonaPlex-GGUF/personaplex-7b-v1-q4_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257347f65ed2cf563d44499144636f7999a78fe9547c27b5eb057b4ce9cc3665
3
+ size 7860681248
PersonaPlex-GGUF/personaplex-7b-v1-q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2263ceacd820450cb825b8063c8dd29d565a3fbd7e7ced2290a58a4286c73b
3
+ size 10944018976
README.md CHANGED
@@ -60,6 +60,7 @@ base_model:
60
  - mlx-community/mel-roformer-mlx
61
  - mlx-community/supertonic-3-mlx
62
  - mlx-community/wavlm-base-plus-mlx
 
63
  - syvai/hviske-v5.3
64
  - nvidia/diar_sortformer_4spk-v1
65
  - nvidia/magpie_tts_multilingual_357m
@@ -116,6 +117,7 @@ for the full matrix and drift notes.
116
  | `Mel-Band-RoFormer-GGUF` | `mel-band-roformer-f16.gguf`, `mel-band-roformer-q8_0.gguf` | `mel_band_roformer` | 16-bit + Q8 drift | MIT |
117
  | `MioCodec-25Hz-44.1kHz-v2-GGUF` | `miocodec-25hz-44khz-v2-orig.gguf`, `miocodec-25hz-44khz-v2-f16.gguf`, `miocodec-25hz-44khz-v2-q8_0.gguf` | `miocodec` | orig pass, 16-bit + Q8 drift | MIT |
118
  | `MioTTS-1.7B-GGUF` | `miotts-1.7b-orig.gguf`, `miotts-1.7b-bf16.gguf`, `miotts-1.7b-q8_0.gguf` | `miotts` | orig pass, 16-bit drift, Q8 ASR-match drift | Apache-2.0 |
 
119
  | `Nemotron-3.5-ASR-Streaming-0.6B-GGUF` | `nemotron-3.5-asr-streaming-0.6b-f16.gguf`, `nemotron-3.5-asr-streaming-0.6b-q8_0.gguf` | `nemotron_asr` | 16-bit pass, Q8 minor filler drift | OpenMDW-1.1 |
120
  | `OmniVoice-GGUF` | `omnivoice-bf16.gguf`, `omnivoice-f16.gguf`, `omnivoice-q8_0.gguf` | `omnivoice` | 16-bit + Q8 drift | Apache-2.0 |
121
  | `Parakeet-TDT-0.6B-v3-GGUF` | `parakeet-tdt-0.6b-v3-f16.gguf`, `parakeet-tdt-0.6b-v3-q8_0.gguf` | `parakeet_tdt` | 16-bit + Q8 pass | CC-BY-4.0 |
 
60
  - mlx-community/mel-roformer-mlx
61
  - mlx-community/supertonic-3-mlx
62
  - mlx-community/wavlm-base-plus-mlx
63
+ - MuScriptor/muscriptor-small
64
  - syvai/hviske-v5.3
65
  - nvidia/diar_sortformer_4spk-v1
66
  - nvidia/magpie_tts_multilingual_357m
 
117
  | `Mel-Band-RoFormer-GGUF` | `mel-band-roformer-f16.gguf`, `mel-band-roformer-q8_0.gguf` | `mel_band_roformer` | 16-bit + Q8 drift | MIT |
118
  | `MioCodec-25Hz-44.1kHz-v2-GGUF` | `miocodec-25hz-44khz-v2-orig.gguf`, `miocodec-25hz-44khz-v2-f16.gguf`, `miocodec-25hz-44khz-v2-q8_0.gguf` | `miocodec` | orig pass, 16-bit + Q8 drift | MIT |
119
  | `MioTTS-1.7B-GGUF` | `miotts-1.7b-orig.gguf`, `miotts-1.7b-bf16.gguf`, `miotts-1.7b-q8_0.gguf` | `miotts` | orig pass, 16-bit drift, Q8 ASR-match drift | Apache-2.0 |
120
+ | `MuScriptor-Small-GGUF` | `muscriptor-small-f32.gguf` | `muscriptor` | F32 pass | CC-BY-NC-4.0 |
121
  | `Nemotron-3.5-ASR-Streaming-0.6B-GGUF` | `nemotron-3.5-asr-streaming-0.6b-f16.gguf`, `nemotron-3.5-asr-streaming-0.6b-q8_0.gguf` | `nemotron_asr` | 16-bit pass, Q8 minor filler drift | OpenMDW-1.1 |
122
  | `OmniVoice-GGUF` | `omnivoice-bf16.gguf`, `omnivoice-f16.gguf`, `omnivoice-q8_0.gguf` | `omnivoice` | 16-bit + Q8 drift | Apache-2.0 |
123
  | `Parakeet-TDT-0.6B-v3-GGUF` | `parakeet-tdt-0.6b-v3-f16.gguf`, `parakeet-tdt-0.6b-v3-q8_0.gguf` | `parakeet_tdt` | 16-bit + Q8 pass | CC-BY-4.0 |