Image-Text-to-Text
Transformers
Safetensors
glm5_next
glm
glm-5
multimodal
vision-language
Mixture of Experts
sparse-attention
mla
quantization
rfa
rfi
rocm
rdna4
gfx1201
4-bit precision
conversational
8-bit precision
Instructions to use djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700") model = AutoModelForMultimodalLM.from_pretrained("djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700
- SGLang
How to use djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700 with Docker Model Runner:
docker model run hf.co/djdeniro/GLM-5.3-Flash-RFA-RFI8-8xR9700
Add GLM-5.3-Flash RFA-RFI8 quantized weights (197.8 GB, 25 shards)
Browse files- .gitattributes +2 -0
- chat_template.jinja +213 -0
- config.json +0 -0
- generation_config.json +12 -0
- model-00000.safetensors +3 -0
- model-00001.safetensors +3 -0
- model-00002.safetensors +3 -0
- model-00003.safetensors +3 -0
- model-00004.safetensors +3 -0
- model-00005.safetensors +3 -0
- model-00006.safetensors +3 -0
- model-00007.safetensors +3 -0
- model-00008.safetensors +3 -0
- model-00009.safetensors +3 -0
- model-00010.safetensors +3 -0
- model-00011.safetensors +3 -0
- model-00012.safetensors +3 -0
- model-00013.safetensors +3 -0
- model-00014.safetensors +3 -0
- model-00015.safetensors +3 -0
- model-00016.safetensors +3 -0
- model-00017.safetensors +3 -0
- model-00018.safetensors +3 -0
- model-00019.safetensors +3 -0
- model-00020.safetensors +3 -0
- model-00021.safetensors +3 -0
- model-00022.safetensors +3 -0
- model-00023.safetensors +3 -0
- model-00024.safetensors +3 -0
- model.safetensors.index.json +3 -0
- processor_config.json +44 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -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 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[gMASK]<sop>
|
| 2 |
+
{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}
|
| 3 |
+
{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
|
| 4 |
+
{%- if tools -%}
|
| 5 |
+
{%- macro tool_to_json(tool) -%}
|
| 6 |
+
{%- set ns_tool = namespace(first=true) -%}
|
| 7 |
+
{{ '{' -}}
|
| 8 |
+
{%- for k, v in tool.items() -%}
|
| 9 |
+
{%- if k != 'defer_loading' and k != 'strict' -%}
|
| 10 |
+
{%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
|
| 11 |
+
{%- set ns_tool.first = false -%}
|
| 12 |
+
"{{ k }}": {{ v | tojson(ensure_ascii=False) }}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- endfor -%}
|
| 15 |
+
{{- '}' -}}
|
| 16 |
+
{%- endmacro -%}
|
| 17 |
+
{%- macro tool_references_to_response(refs) -%}
|
| 18 |
+
{{- '<tool_response><tools>\n' -}}
|
| 19 |
+
{%- for tr in refs -%}
|
| 20 |
+
{%- for tool in tools -%}
|
| 21 |
+
{%- if 'function' in tool -%}
|
| 22 |
+
{%- set tool = tool['function'] -%}
|
| 23 |
+
{%- endif -%}
|
| 24 |
+
{%- if tool.name == tr.name -%}
|
| 25 |
+
{{- tool_to_json(tool) + '\n' -}}
|
| 26 |
+
{%- endif -%}
|
| 27 |
+
{%- endfor -%}
|
| 28 |
+
{%- endfor -%}
|
| 29 |
+
{{- '</tools></tool_response>' -}}
|
| 30 |
+
{%- endmacro -%}
|
| 31 |
+
<|system|>
|
| 32 |
+
# Tools
|
| 33 |
+
|
| 34 |
+
You may call one or more functions to assist with the user query.
|
| 35 |
+
|
| 36 |
+
You are provided with function signatures within <tools></tools> XML tags:
|
| 37 |
+
<tools>
|
| 38 |
+
{% for tool in tools %}
|
| 39 |
+
{%- if 'function' in tool -%}
|
| 40 |
+
{%- set tool = tool['function'] -%}
|
| 41 |
+
{%- endif -%}
|
| 42 |
+
{% if tool.defer_loading is not defined or not tool.defer_loading %}
|
| 43 |
+
{{ tool_to_json(tool) }}
|
| 44 |
+
{% endif %}
|
| 45 |
+
{% endfor %}
|
| 46 |
+
</tools>
|
| 47 |
+
|
| 48 |
+
For each function call, output the function name and arguments within the following XML format:
|
| 49 |
+
<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}
|
| 50 |
+
{%- macro visible_text(content) -%}
|
| 51 |
+
{%- if content is string -%}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{%- elif content is iterable and content is not mapping -%}
|
| 54 |
+
{%- for item in content -%}
|
| 55 |
+
{%- if item is mapping and item.type == 'text' -%}
|
| 56 |
+
{{- item.text }}
|
| 57 |
+
{%- elif item is string -%}
|
| 58 |
+
{{- item }}
|
| 59 |
+
{%- elif item is mapping and item.type in ['image', 'image_url'] -%}
|
| 60 |
+
{{- '<|begin_of_image|><|image|><|end_of_image|>' }}
|
| 61 |
+
{%- elif item is mapping and item.type in ['video', 'video_url'] -%}
|
| 62 |
+
{{- '<|begin_of_video|><|video|><|end_of_video|>' }}
|
| 63 |
+
{%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}
|
| 64 |
+
{{- '<|begin_of_audio|><|end_of_audio|>' }}
|
| 65 |
+
{%- endif -%}
|
| 66 |
+
{%- endfor -%}
|
| 67 |
+
{%- else -%}
|
| 68 |
+
{{- content }}
|
| 69 |
+
{%- endif -%}
|
| 70 |
+
{%- endmacro -%}
|
| 71 |
+
{%- macro tool_response(text) -%}
|
| 72 |
+
{{- '<tool_response>' + text + '</tool_response>' -}}
|
| 73 |
+
{%- endmacro -%}
|
| 74 |
+
{%- macro render_tool_response(m) -%}
|
| 75 |
+
{%- if m.content is string -%}
|
| 76 |
+
{{- tool_response(m.content) -}}
|
| 77 |
+
{%- elif m.content and m.content is not mapping and m.content.0.type == "tool_reference" -%}
|
| 78 |
+
{{- tool_references_to_response(m.content) -}}
|
| 79 |
+
{%- elif is_list_of_outputs(m) -%}
|
| 80 |
+
{%- for tr in m.content -%}
|
| 81 |
+
{%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == "tool_reference" -%}
|
| 82 |
+
{{- tool_references_to_response(tr.output) -}}
|
| 83 |
+
{%- else -%}
|
| 84 |
+
{{- tool_response(visible_text(tr.output)) -}}
|
| 85 |
+
{%- endif -%}
|
| 86 |
+
{%- endfor -%}
|
| 87 |
+
{%- else -%}
|
| 88 |
+
{{- tool_response(visible_text(m.content)) -}}
|
| 89 |
+
{%- endif -%}
|
| 90 |
+
{%- endmacro -%}
|
| 91 |
+
{%- macro id_of(obj) -%}
|
| 92 |
+
{%- if obj.tool_call_id -%}
|
| 93 |
+
{{- obj.tool_call_id -}}
|
| 94 |
+
{%- elif obj.id -%}
|
| 95 |
+
{{- obj.id -}}
|
| 96 |
+
{%- endif -%}
|
| 97 |
+
{%- endmacro -%}
|
| 98 |
+
{%- macro is_list_of_outputs(m) -%}
|
| 99 |
+
{%- if m.content and m.content.0.output is defined -%}1{%- endif -%}
|
| 100 |
+
{%- endmacro -%}
|
| 101 |
+
{%- set ns = namespace(last_user_index=-1) -%}
|
| 102 |
+
{%- for m in messages %}
|
| 103 |
+
{%- if m.role == 'user' %}
|
| 104 |
+
{%- set ns.last_user_index = loop.index0 -%}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- endfor %}
|
| 107 |
+
{%- for m in messages -%}
|
| 108 |
+
{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
|
| 109 |
+
{%- elif m.role == 'assistant' -%}
|
| 110 |
+
<|assistant|>
|
| 111 |
+
{%- set content = visible_text(m.content) %}
|
| 112 |
+
{%- if m.reasoning_content is string %}
|
| 113 |
+
{%- set reasoning_content = m.reasoning_content %}
|
| 114 |
+
{%- elif '</think>' in content %}
|
| 115 |
+
{%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
|
| 116 |
+
{%- set content = content.split('</think>')[-1] %}
|
| 117 |
+
{%- endif %}
|
| 118 |
+
{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
|
| 119 |
+
{{ '<think>' + reasoning_content + '</think>'}}
|
| 120 |
+
{%- else -%}
|
| 121 |
+
{{ '<think></think>' }}
|
| 122 |
+
{%- endif -%}
|
| 123 |
+
{%- if content.strip() -%}
|
| 124 |
+
{{ content.strip() }}
|
| 125 |
+
{%- endif -%}
|
| 126 |
+
{% if m.tool_calls %}
|
| 127 |
+
{% for tc in m.tool_calls %}
|
| 128 |
+
{%- if tc.function %}
|
| 129 |
+
{%- set tc = tc.function %}
|
| 130 |
+
{%- endif %}
|
| 131 |
+
{{- '<tool_call>' + tc.name -}}
|
| 132 |
+
{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}
|
| 133 |
+
{% endif %}
|
| 134 |
+
{%- elif m.role == 'tool' -%}
|
| 135 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 136 |
+
{{- '<|observation|>' -}}
|
| 137 |
+
{%- set block_start = loop.index0 -%}
|
| 138 |
+
{%- set ns_blk = namespace(end=block_start) -%}
|
| 139 |
+
{%- for j in range(block_start, messages|length) -%}
|
| 140 |
+
{%- if messages[j].role == 'tool' -%}
|
| 141 |
+
{%- set ns_blk.end = j -%}
|
| 142 |
+
{%- else -%}
|
| 143 |
+
{%- break -%}
|
| 144 |
+
{%- endif -%}
|
| 145 |
+
{%- endfor -%}
|
| 146 |
+
{%- set ns_a = namespace(tool_calls=none) -%}
|
| 147 |
+
{%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}
|
| 148 |
+
{%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}
|
| 149 |
+
{%- endif -%}
|
| 150 |
+
{%- set ns_chk = namespace(can_sort=true) -%}
|
| 151 |
+
{%- if not ns_a.tool_calls -%}
|
| 152 |
+
{%- set ns_chk.can_sort = false -%}
|
| 153 |
+
{%- else -%}
|
| 154 |
+
{%- for k in range(block_start, ns_blk.end + 1) -%}
|
| 155 |
+
{%- set m = messages[k] -%}
|
| 156 |
+
{%- if is_list_of_outputs(m) -%}
|
| 157 |
+
{%- for entry in m.content -%}
|
| 158 |
+
{%- set eid = id_of(entry) -%}
|
| 159 |
+
{%- if not eid -%}
|
| 160 |
+
{%- set ns_chk.can_sort = false -%}
|
| 161 |
+
{%- endif -%}
|
| 162 |
+
{%- endfor -%}
|
| 163 |
+
{%- else -%}
|
| 164 |
+
{%- set tk_id = id_of(m) -%}
|
| 165 |
+
{%- if not tk_id -%}
|
| 166 |
+
{%- set ns_chk.can_sort = false -%}
|
| 167 |
+
{%- endif -%}
|
| 168 |
+
{%- endif -%}
|
| 169 |
+
{%- endfor -%}
|
| 170 |
+
{%- for tc in ns_a.tool_calls -%}
|
| 171 |
+
{%- set tc_id = id_of(tc) -%}
|
| 172 |
+
{%- if not tc_id -%}
|
| 173 |
+
{%- set ns_chk.can_sort = false -%}
|
| 174 |
+
{%- endif -%}
|
| 175 |
+
{%- endfor -%}
|
| 176 |
+
{%- endif -%}
|
| 177 |
+
{%- if ns_chk.can_sort -%}
|
| 178 |
+
{%- for tc in ns_a.tool_calls -%}
|
| 179 |
+
{%- set tc_id = id_of(tc) -%}
|
| 180 |
+
{%- for k in range(block_start, ns_blk.end + 1) -%}
|
| 181 |
+
{%- set m = messages[k] -%}
|
| 182 |
+
{%- if is_list_of_outputs(m) -%}
|
| 183 |
+
{%- for entry in m.content -%}
|
| 184 |
+
{%- set eid = id_of(entry) -%}
|
| 185 |
+
{%- if eid == tc_id -%}
|
| 186 |
+
{%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == "tool_reference" -%}
|
| 187 |
+
{{- tool_references_to_response(entry.output) -}}
|
| 188 |
+
{%- else -%}
|
| 189 |
+
{{- tool_response(visible_text(entry.output)) -}}
|
| 190 |
+
{%- endif -%}
|
| 191 |
+
{%- endif -%}
|
| 192 |
+
{%- endfor -%}
|
| 193 |
+
{%- else -%}
|
| 194 |
+
{%- set tk_id = id_of(m) -%}
|
| 195 |
+
{%- if tk_id == tc_id -%}
|
| 196 |
+
{{- render_tool_response(m) -}}
|
| 197 |
+
{%- endif -%}
|
| 198 |
+
{%- endif -%}
|
| 199 |
+
{%- endfor -%}
|
| 200 |
+
{%- endfor -%}
|
| 201 |
+
{%- else -%}
|
| 202 |
+
{%- for k in range(block_start, ns_blk.end + 1) -%}
|
| 203 |
+
{{- render_tool_response(messages[k]) -}}
|
| 204 |
+
{%- endfor -%}
|
| 205 |
+
{%- endif -%}
|
| 206 |
+
{% endif -%}
|
| 207 |
+
{%- elif m.role == 'system' -%}
|
| 208 |
+
<|system|>{{ visible_text(m.content) }}
|
| 209 |
+
{%- endif -%}
|
| 210 |
+
{%- endfor -%}
|
| 211 |
+
{%- if add_generation_prompt -%}
|
| 212 |
+
<|assistant|>{{- '<think>' -}}
|
| 213 |
+
{%- endif -%}
|
config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
154820,
|
| 5 |
+
154827,
|
| 6 |
+
154829
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 154820,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "5.16.0"
|
| 12 |
+
}
|
model-00000.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b889c4892e7c7c00e0af63ed396d180f28954c906a292f17b9a46ed32099c503
|
| 3 |
+
size 5372952032
|
model-00001.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a710a523cf4b0580ddb8f19129b6b10640390f5644f2dce3a79c85ec26be6464
|
| 3 |
+
size 5368754216
|
model-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39faf2065f16ad8f2292412f8304b5b00b011c81fd01ca318b68f9b8f95744e7
|
| 3 |
+
size 5368754048
|
model-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfd5cb6c103152d4ed42fae08eaa90f5d04211908f2c6d1f63d4a9b96155db1d
|
| 3 |
+
size 7736921304
|
model-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6a0860a52cf333a953007c4ce5d36b3a59a2a13db6bddde7c8c55b42b3c67cb
|
| 3 |
+
size 8495060840
|
model-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7ad0e184611b5eb21b9172a5dc51cd1a25f793efacc023e3c235f3e4b146cd1
|
| 3 |
+
size 8481422752
|
model-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dd11c04dfccfe4df4b724f8a5c2996b76d6f9a4def7b8221d6a42a30c548bc4
|
| 3 |
+
size 8495060840
|
model-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdfe3e73fcd9f6ffe888e134b04b4ba18d74f4525b59e8c58dae2c542e5dac51
|
| 3 |
+
size 8481428000
|
model-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e4a39b8d2357c4ea24aca287c51a3baabf3e824905b5ad8ffbb35dbc7aa3040
|
| 3 |
+
size 8495066096
|
model-00009.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec738bc87d863a6c538a91c762c3c36e806c6d59ac1b60abf387be66dd3a7b8e
|
| 3 |
+
size 8481428000
|
model-00010.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46a9e70ef50714f5d77bb4aa23bc22b0398ce9384e7229b64de7c8db52f9b47a
|
| 3 |
+
size 8495066096
|
model-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a848529ce786626145cab64eacd086d24b04b559ef704f811492f0209daa9bd6
|
| 3 |
+
size 8481428000
|
model-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4131dc98088c313aaade5f05bf6d59f42ea0fd91d67ca75fa8bc52431ca56b
|
| 3 |
+
size 8495066096
|
model-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c46ad1768197a99f5995685d9ede70991c99c37b951f1cf1d88244dab23d96d
|
| 3 |
+
size 8481428000
|
model-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57e0791d2e7095751ac69bc29f9f2c8112f1c1dd66ec6d1165244fed8fa5ceb5
|
| 3 |
+
size 8495066096
|
model-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84087de4378a2ba95be77bc4bfb8b6b68c4330a8221a934348efcf54f01cadc1
|
| 3 |
+
size 8481428000
|
model-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2da0c023fe728c87d310bfd49775ceea4cb0dba46b1f8764f2f272a26d8344b0
|
| 3 |
+
size 8495066096
|
model-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7d9a1f08efe10dac505047db034b9cdd32b6bcf55df0643cc634dcd821db500
|
| 3 |
+
size 8481428000
|
model-00018.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bbd474a5c77157b87267107141d5082b8ca49d02a1a4ea8686c2cb15276fad4
|
| 3 |
+
size 8495066096
|
model-00019.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ac59b1edd149af30cf35feebfdf6d53c627461fcf5d91a235cbe7fdb3b9502e
|
| 3 |
+
size 8481428000
|
model-00020.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2646a263a9d701bc4e44e06fd85db1fedf633c40d63eec6ff0a8cefd06095aaa
|
| 3 |
+
size 8495066096
|
model-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f25f83ea2b3a5a74388ff67acd605a9f2bcdc8b03a0ceab973b03ad9800986e5
|
| 3 |
+
size 8481428000
|
model-00022.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:713052fef0e521a4c6be79f3d3d392c13822e32656b2a10172ab727d3fd59ca7
|
| 3 |
+
size 8495066096
|
model-00023.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c62130b33202d7ef6d50b82469e3a75a371d6cc4c961ba5c722175628b6db285
|
| 3 |
+
size 8481428000
|
model-00024.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab7efa2ed4ce294409daf077ddedb464dc653acb673e1e95b9c62cdcb10b49b5
|
| 3 |
+
size 4247532136
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58a6c5b26a88d102f1cda24b45d4ab329e613919e5c9fdcadb43bc7b67e3ac68
|
| 3 |
+
size 11253844
|
processor_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"patch_expand_factor": 1,
|
| 5 |
+
"merge_size": 2,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.26862954,
|
| 13 |
+
0.26130258,
|
| 14 |
+
0.27577711
|
| 15 |
+
],
|
| 16 |
+
"temporal_patch_size": 2,
|
| 17 |
+
"patch_size": 14,
|
| 18 |
+
"min_image_tokens": 16,
|
| 19 |
+
"max_image_tokens": 8000,
|
| 20 |
+
"image_processor_type": "Glm5NextImageProcessor"
|
| 21 |
+
},
|
| 22 |
+
"video_processor": {
|
| 23 |
+
"do_rescale": true,
|
| 24 |
+
"video_processor_type": "Glm5NextVideoProcessor",
|
| 25 |
+
"patch_expand_factor": 1,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"image_mean": [
|
| 28 |
+
0.48145466,
|
| 29 |
+
0.4578275,
|
| 30 |
+
0.40821073
|
| 31 |
+
],
|
| 32 |
+
"image_std": [
|
| 33 |
+
0.26862954,
|
| 34 |
+
0.26130258,
|
| 35 |
+
0.27577711
|
| 36 |
+
],
|
| 37 |
+
"temporal_patch_size": 2,
|
| 38 |
+
"patch_size": 14,
|
| 39 |
+
"min_image_tokens": 16,
|
| 40 |
+
"max_image_tokens": 240000,
|
| 41 |
+
"fps": 2
|
| 42 |
+
},
|
| 43 |
+
"processor_class": "Glm5NextProcessor"
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
|
| 3 |
+
size 20217442
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<|endoftext|>",
|
| 8 |
+
"[MASK]",
|
| 9 |
+
"[gMASK]",
|
| 10 |
+
"[sMASK]",
|
| 11 |
+
"<sop>",
|
| 12 |
+
"<eop>",
|
| 13 |
+
"<|system|>",
|
| 14 |
+
"<|user|>",
|
| 15 |
+
"<|assistant|>",
|
| 16 |
+
"<|observation|>",
|
| 17 |
+
"<|begin_of_image|>",
|
| 18 |
+
"<|end_of_image|>",
|
| 19 |
+
"<|begin_of_video|>",
|
| 20 |
+
"<|end_of_video|>",
|
| 21 |
+
"<|begin_of_audio|>",
|
| 22 |
+
"<|end_of_audio|>",
|
| 23 |
+
"<|begin_of_transcription|>",
|
| 24 |
+
"<|end_of_transcription|>"
|
| 25 |
+
],
|
| 26 |
+
"is_local": true,
|
| 27 |
+
"model_max_length": 1048576,
|
| 28 |
+
"model_specific_special_tokens": {},
|
| 29 |
+
"pad_token": "<|endoftext|>",
|
| 30 |
+
"padding_side": "left",
|
| 31 |
+
"remove_space": false,
|
| 32 |
+
"tokenizer_class": "TokenizersBackend"
|
| 33 |
+
}
|