MiniCPM-V-4.6: minicpmv46_vlm_decode_int8lin bundle
Browse files- .gitattributes +2 -0
- gpu-pipelined/minicpmv46_vlm_decode_int8lin/metadata.json +28 -0
- gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/main.hash +1 -0
- gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/main.mlirb +3 -0
- gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/metadata.json +3 -0
- gpu-pipelined/minicpmv46_vlm_decode_int8lin/tokenizer/tokenizer.json +3 -0
- gpu-pipelined/minicpmv46_vlm_decode_int8lin/tokenizer/tokenizer_config.json +42 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,5 @@ saved_model/**/* 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 |
gpu-pipelined/minicpmv46_vision/minicpmv46_vision.aimodel/main.mlirb 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 |
gpu-pipelined/minicpmv46_vision/minicpmv46_vision.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
gpu-pipelined/minicpmv46_vlm_decode_int8lin/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
gpu-pipelined/minicpmv46_vlm_decode_int8lin/metadata.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata_version": "0.2",
|
| 3 |
+
"kind": "llm",
|
| 4 |
+
"name": "minicpmv46_vlm_decode_int8lin",
|
| 5 |
+
"assets": {
|
| 6 |
+
"main": "minicpmv46_vlm_decode_int8lin.aimodel"
|
| 7 |
+
},
|
| 8 |
+
"language": {
|
| 9 |
+
"tokenizer": "openbmb/MiniCPM-V-4.6",
|
| 10 |
+
"vocab_size": 248094,
|
| 11 |
+
"max_context_length": 4096,
|
| 12 |
+
"embedded_tokenizer": true,
|
| 13 |
+
"function_map": {
|
| 14 |
+
"main": [
|
| 15 |
+
"main"
|
| 16 |
+
]
|
| 17 |
+
}
|
| 18 |
+
},
|
| 19 |
+
"vlm": {
|
| 20 |
+
"image_embeds": "[64,1024] static buffer; image ids = V+slot"
|
| 21 |
+
},
|
| 22 |
+
"source": {
|
| 23 |
+
"hf_model_id": "openbmb/MiniCPM-V-4.6"
|
| 24 |
+
},
|
| 25 |
+
"compilation": {
|
| 26 |
+
"date": "2026-06-14T01:15:21.610369+00:00"
|
| 27 |
+
}
|
| 28 |
+
}
|
gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/main.hash
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
[4�I7�U={&ܔV����jJ�X��[�#���
|
gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/main.mlirb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b349d49379a553d7b26dc9456d102eaf8c06a4af05889b05bc32305adcad41d
|
| 3 |
+
size 1038389246
|
gpu-pipelined/minicpmv46_vlm_decode_int8lin/minicpmv46_vlm_decode_int8lin.aimodel/metadata.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"assetVersion" : "2.0"
|
| 3 |
+
}
|
gpu-pipelined/minicpmv46_vlm_decode_int8lin/tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33861e37bb955af1e3f3061182b820f347eba2b9c2c1011c82794bf0d6e77b54
|
| 3 |
+
size 19992481
|
gpu-pipelined/minicpmv46_vlm_decode_int8lin/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": "<|im_start|>",
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"extra_special_tokens": {
|
| 12 |
+
"image_token": "<|image_pad|>",
|
| 13 |
+
"video_token": "<|video_pad|>",
|
| 14 |
+
"image_start_token": "<image>",
|
| 15 |
+
"image_end_token": "</image>",
|
| 16 |
+
"slice_start_token": "<slice>",
|
| 17 |
+
"slice_end_token": "</slice>",
|
| 18 |
+
"image_id_start_token": "<image_id>",
|
| 19 |
+
"image_id_end_token": "</image_id>"
|
| 20 |
+
},
|
| 21 |
+
"image_token": "<|image_pad|>",
|
| 22 |
+
"is_local": true,
|
| 23 |
+
"model_max_length": 262144,
|
| 24 |
+
"model_specific_special_tokens": {
|
| 25 |
+
"audio_bos_token": "<|audio_start|>",
|
| 26 |
+
"audio_eos_token": "<|audio_end|>",
|
| 27 |
+
"audio_token": "<|audio_pad|>",
|
| 28 |
+
"image_token": "<|image_pad|>",
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
},
|
| 33 |
+
"pad_token": "<|endoftext|>",
|
| 34 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 35 |
+
"split_special_tokens": false,
|
| 36 |
+
"unk_token": "<unk>",
|
| 37 |
+
"video_token": "<|video_pad|>",
|
| 38 |
+
"vision_bos_token": "<|vision_start|>",
|
| 39 |
+
"vision_eos_token": "<|vision_end|>",
|
| 40 |
+
"chat_template": "{%- if enable_thinking is not defined -%}\n {%- set enable_thinking = false -%}\n{%- endif -%}\n{%- macro render_content(content, is_system_content=false) -%}\n {%- if content is string -%}\n {{- content -}}\n {%- elif content is iterable and content is not mapping -%}\n {%- set ns = namespace(parts=[]) -%}\n {%- for item in content -%}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' -%}\n {%- if is_system_content -%}\n {{- raise_exception('System message cannot contain images.') -}}\n {%- endif -%}\n {%- set ns.parts = ns.parts + ['<|image_pad|>'] -%}\n {%- elif 'video' in item or item.type == 'video' -%}\n {%- if is_system_content -%}\n {{- raise_exception('System message cannot contain videos.') -}}\n {%- endif -%}\n {%- set ns.parts = ns.parts + ['<|video_pad|>'] -%}\n {%- elif 'text' in item -%}\n {%- set ns.parts = ns.parts + [item.text] -%}\n {%- else -%}\n {{- raise_exception('Unexpected item type in content.') -}}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.parts | join('\\n') -}}\n {%- elif content is none or content is undefined -%}\n {{- '' -}}\n {%- else -%}\n {{- raise_exception('Unexpected content type.') -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}\n",
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer"
|
| 42 |
+
}
|