Add files using upload-large-folder tool

README.md

@@ -0,0 +1,22 @@
+---
+tags:
+- mlx
+- transformers
+- quantization
+- dq3
+---
+
+# GLM-5_dq3
+
+This model is a DQ3 quantized version of the original model [GLM-5](Local Model).
+It was quantized locally using the `mlx_lm` library.
+
+## Quantization Methodology (DQ3)
+
+This model was quantized using the dynamic **DQ3** (3-bit / 4-bit / 8-bit mixed) approach, inspired by the methodology described in the [mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8](https://huggingface.co/mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8) repository.
+
+The weights are mixed based on MLX layers:
+- Expert layers (switch_mlp / mlp) are quantized to 3-bit.
+- The first 5 layers are kept at higher quality (5-bit).
+- Every 5th layer is medium quality (4-bit).
+- All other layers (e.g. attention, normalization) remain at 8-bit to serve as the "8-bit brain".

chat_template.jinja

@@ -0,0 +1,86 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<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 -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
+{{ '<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '</think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{- '<tool_call>' + tc.name -}}
+{% 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 %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '<tool_response>' }}
+{{- m.content }}
+{{- '</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
+{%- endif -%}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.0.2.dev0"
+}

model-00001-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dec22079da525601a6ba1f8698f22c61c42774ba7ba55967979b5437836ffed
+size 4915364965

model-00002-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde7f77c03bd6c485e63bf6468d697b03a17a44d02ea1b6e4977eb1d07652028
+size 5261747030

model-00003-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dd4e8d7000f86aaa66aa865a08984810ec9b75b16c46bfe73e667952e83ddc
+size 5261747026

model-00004-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca67c0a45dc565b1a0b88a86361f6043a89938abd9fdfbf13086976b3a926db0
+size 4859093844

model-00005-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab9be94074241c718c5412e6f6cd60a08f973b25ad8cea0a3c75809d1eaf40b
+size 4456440658

model-00006-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcef45049d11366bff4b58432edead569adf852430d7604b19a506905b97f033
+size 4456440658

model-00007-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2f1e7c9566803524c6766559ae2ee59b2eee4dbd007136bd1ec8e6984579a6
+size 4456440662

model-00008-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:760d7d4bed4a7aed7a91c9bd8decbe02da871eaf33c0debaa99ab3acfd6d0dbb
+size 4456440695

model-00009-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec165b1381ded6e776446b5ab514d05c01bce14091676ef6b6ecb508802f618b
+size 4859093895

model-00010-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011ab9d627679a27c3356f9c5a2b5caff074a5d65d4117847798d1041cb61977
+size 4456440661

model-00011-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0662de76b63aedfab0a4479a9c6ca5edaac101de2ae195f119eeb8c764eeb6b9
+size 4456440715

model-00012-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7141ba1c3dc21e080dadabe0768113c8327f22947f9983059d7888ba8dbb45
+size 4456440715

model-00013-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8fe22dd689a43649db552d73f50bb7b6dd82ebe40f974a59a87cb0ce09ca34
+size 4456440715

model-00014-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4aab02f2c059618a04e1a5c95341603b0459e57fa0dfdcf14ce2d83cbe8d6f
+size 4859093897

model-00015-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8021ea73c5d2c9fe95cc21f6fe75fbd83aec17bdface95de5d2905a379f43f4e
+size 4456440717

model-00016-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8805678870b2dd9b0e1826c8b9c7d18a3b3fa3f4490c19cf09238d9f5decd6f
+size 4456440713

model-00017-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccffb05fb961774e3fc4699fc1a50ebf3679d5899cf427fdd77a0828f61f437
+size 4456440707

model-00018-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90609f1255e6fe07d13056959045ec1f960e513fa6524b4c9ae189f55ac9aa34
+size 4456440709

model-00019-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2972a1ff78b056b0c221a87a1f097a202cae8dffffe0d6805c6a414243f9ba
+size 4859093901

model-00020-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ce2cc619c1a4cb663f92a303b289430ece3667ad1f513882e5c90853a4a653
+size 4456440715

model-00021-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc7d30e8f185c6144e00a32c32644cd4800c13cc7db130e54836ae4e694c109
+size 4456440713

model-00022-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e557f55402cf49344cc9a8dce28ec11b849b201fdb360710c42081cfe4763bec
+size 4456440713

model-00023-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934fcb7277d5cfaaab814b45148d758705b26716a79c52f9d87d0873feb939d4
+size 4456440715

model-00024-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e883233ef28bbe79a7b5c58bed4b00ce80c1795ed1e6b1f590bc3c5446fe26
+size 4859093899

model-00025-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4768f9181796dec27c52c866003916ddfb2eee8c044554617f5bd2606520b1
+size 4456440715

model-00026-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f45b950671f274084485a57facd2464ca606b1871d306b34a3c7707be8eef6
+size 4456440715

model-00027-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6064d6ee2c01afc9aeffc98f1224d04b0139bc8a9e3a6c711f92a4a8e0a25221
+size 4456440715

model-00028-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1f1d7cb0ab604d3cf25943e563951be925bbc4148a80fa0274c95fe1ac7303
+size 4456440713

model-00029-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8947e846796d9f2f55ef42d71833ba990d243e3d4a1b2777ad27588a59300f2
+size 4859093899

model-00030-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09e58842998d8150f076d41517bfd852cd98a59ea4c5015db07f2089bc2412f
+size 4456440717

model-00031-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e90fae0ac623974e3b427f0cc441d43889712ef5705d0e73fc9e7c073b1f89
+size 4456440709

model-00032-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b729330001f1d75286ac6399e059b71fc4cb79feee05e2a030d2ef7f7ff72b10
+size 4456440713

model-00033-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72064e669e5138116a971422215b6f0a07ef0be873ef70ae7f9302bf24365f45
+size 4456440689

model-00034-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42c199ec40dd29c49050a775c19653577ff88fb716d5fbcf93902c7ebba7a9e
+size 4859093867

model-00035-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094d26da85b8b59d16eca233361fe7ac53b36801ca5b9d09366c30bfc764007a
+size 4456440715

model-00036-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c28c84b8b25e184e3d1e58a7f324b7750d492269bbf9514c2b1f80f5fc2adc
+size 4456440713

model-00037-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c83545680b8a2c97d9951b184e8b26f8e6ee7bdab735421e641b30707b64467
+size 4456440715

model-00038-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c77e03a81923465997cef33788da50c97533e8483a4db50ca3e4a7b69cc778f
+size 4456440715

model-00039-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8291679c941b4fd3e0e42bbca249d4640a9e775aa215a1388c3eaf84641e541d
+size 4859093895

model-00040-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb683e983eef4328d33ecbb984a70f6099444ffc77310f203fb8bbc0df3f630e
+size 4456440715

model-00041-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1d6ad823fd4031ef7448990e3fb30042ac93a4bbf3b3b7a60edd9709a45505
+size 4456440715

model-00073-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71489e563ba422edf9fb1c36abbe48dddc2cc8415e6422d06f4768d708af2441
+size 4456440713

model-00074-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e70f16d871e7a7774eddda21c0a4c82e7bb04aa0ce76cd9c7061c9f175b69a
+size 4859093899

model-00075-of-00076.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca267a61f7092c459134303399c6f7abd05cde2b3a7e0bb48ab667e92b4acab3
+size 4456440709

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>"
+  ],
+  "is_local": true,
+  "model_max_length": 202752,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "glm47"
+}