Add files using upload-large-folder tool

README.md

@@ -0,0 +1,22 @@
+---
+tags:
+- mlx
+- transformers
+- quantization
+- dq4
+---
+
+# GLM-5.1-FP8_dq4
+
+This model is a DQ4 quantized version of the original model [GLM-5.1-FP8](Local Model).
+It was quantized locally using the `mlx_lm` library.
+
+## Quantization Methodology (DQ4)
+
+This model was quantized using the dynamic **DQ4** (4-bit / 5-bit / 6-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 4-bit.
+- The first 5 layers are kept at higher quality (6-bit).
+- Every 5th layer is medium quality (5-bit).
+- All other layers (e.g. attention, normalization) remain at 8-bit to serve as the "8-bit brain".

chat_template.jinja

@@ -0,0 +1,117 @@
+[gMASK]<sop>
+{%- if tools -%}
+{%- macro tool_to_json(tool) -%}
+    {%- set ns_tool = namespace(first=true) -%}
+    {{ '{' -}}
+    {%- for k, v in tool.items() -%}
+        {%- if k != 'defer_loading' and k != 'strict' -%}
+            {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
+            {%- set ns_tool.first = false -%}
+            "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- endmacro -%}
+<|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 %}
+{%- if 'function' in tool -%}
+    {%- set tool = tool['function'] -%}
+{%- endif -%}
+{% if tool.defer_loading is not defined or not tool.defer_loading %}
+{{ tool_to_json(tool) }}
+{% endif %}
+{% 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, thinking_indices='') -%}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- elif m.role == 'assistant' %}
+        {%- if m.reasoning_content is string %}
+            {%- set ns.thinking_indices = ns.thinking_indices ~ ',' ~ ns.last_user_index ~ ',' -%}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- set ns.has_thinking = false -%}
+{%- for m in messages -%}
+{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}{% set ns.has_thinking = (',' ~ loop.index0 ~ ',') in ns.thinking_indices -%}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- elif '</think>' in content %}
+    {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
+    {%- set content = content.split('</think>')[-1] %}
+{%- elif loop.index0 > ns.last_user_index and not (enable_thinking is defined and not enable_thinking) %}
+    {%- set reasoning_content = '' %}
+{%- elif loop.index0 < ns.last_user_index and ns.has_thinking %}
+    {%- set reasoning_content = '' %}
+{%- endif %}
+{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
+{{ '<think>' + reasoning_content +  '</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 loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' -}}
+{%- endif %}
+{%- if m.content is string -%}
+    {{- '<tool_response>' + m.content + '</tool_response>' -}}
+{%- else -%}
+    {{- '<tool_response><tools>\n' -}}
+    {% for tr in m.content %}
+        {%- for tool in tools -%}
+            {%- if 'function' in tool -%}
+                {%- set tool = tool['function'] -%}
+            {%- endif -%}
+            {%- if tool.name == tr.name -%}
+                {{- tool_to_json(tool) + '\n' -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endfor -%}
+    {{- '</tools></tool_response>' -}}
+{% 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": "5.4.0"
+}

model-00001-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6c9c22b8441e66b3905d4b76f695c23ba5fd518996fda1bffae5290e27de31
+size 3993666268

model-00002-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336a49f935ecc63844108ed1d98fedf0326e7870ee5a7345a723567e522b18e4
+size 4657766757

model-00003-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8b5bca406fcd53a3264952047c881047edac3e4fdbffa4766facdc41ea4414
+size 3623879442

model-00004-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cfd68ee5081a9b7b8a989c5aca159aa51ce2d833856f1e4947e9d791b49578
+size 4657766879

model-00005-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5852ffbedf9d6a073f49a349413abe51896776b5634ce5ffba3a99962ae7d56
+size 4255113603

model-00006-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ec2061bed838aff4c1c69a5b5a7d94b8236124cb5214b0fa635707fa63bade
+size 5335155728

model-00007-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60619e2522386bc8fede1a5a9fc515f5932512e9ae04727c71b19bad2fe5a78e
+size 3953123926

model-00008-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4c15ea7697b71e5c74d558a9854103839ddfde38ebdbcf4208b9514e4058a9
+size 3852460509

model-00009-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75a14d695edef9aae0d677326fd14334a49d95086c29166aa1557a32233a3cb
+size 3852460387

model-00010-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925f609e4a171f9ac16121d2ba8baba2e54dacfa7020c8791118359789f260aa
+size 5335155726

model-00011-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:914665eb012b51bc5a53eb144eeb0d287a9fbf2c4276abedb69ad7569cb76b31
+size 3953123963

model-00012-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20afca3f9f0b3b4d7c1de73a5172c1d5c279f13d9c83340478636a259594fad
+size 4255113743

model-00013-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efd1e99221cb9edcceb8b8e9934c775ba5c0333a89000a29f1cb96b660d418b
+size 3852460545

model-00014-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7fa9a171bc8595b43674851c24c0dd310ed1ae7b4ec7beba09dddf6d143d27
+size 5335155736

model-00015-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f987b4d7e8e6746c9d2c8b9a0314616990611292e2c896878f1fe47e3e6dc4f
+size 3953123979

model-00016-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296d6e3216899d661f96472c69cd192353c3615767feec4e7bfec2a41c67e46b
+size 3852460539

model-00017-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5508078b3bd21417878ae3583b50f026e6de1d599f4554107773fdccaa01b8
+size 3852460473

model-00018-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692d8413568eff12f9a370968a66fbb9fd4aebd79519726d40bd60a6a8113061
+size 3623879442

model-00019-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c55cc6ebcdc6879e4832449c3f56274ea8f9935ffc77ebb0f19ddc8c7053f37
+size 4255113745

model-00020-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f98299f23d471c32592e81a657c3551f54fe7d126a025570caa55962020bad
+size 3852460461

model-00021-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90302d8f535302472907e4bffafd55293ec895acf94961a6bbc13174be475e34
+size 5335155738

model-00022-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f857c09fee9df13900c815c261ed5d30b2d63a9dcd054c8cb7a5e2b0bbe66eaf
+size 3953123893

model-00023-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17709d6e635cd4bcf31fd006dad0278eeca312954be888a2023d0c11204ddfa7
+size 3852460555

model-00024-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac362bb2d31778a5682bb1befb0ab299b33e720063d04378d7a0c58ca4564d29
+size 3852460537

model-00025-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c76bc56abf657fc8c64933817b780881aa0ae933e6eaae45d0408bc94637089
+size 3623879444

model-00026-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd4881da2afb4b05fa958e346fe1371d2d769b7aae4c55eec7f077920251eb7
+size 4255113745

model-00027-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff2f642c7a3b43e554621f1886adf5bf11a3338e47d9f5d95d9c6b60cbf6064
+size 3852460513

model-00028-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d3a477b2a73fbb8eab463422899cf623f67a62e8fd66cd740d219ad84cb537
+size 5335155734

model-00029-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0802f7f4fdd6563dfb584e921136b853c8521b828a98476996e5691807e6407c
+size 3953123973

model-00030-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e0f451bc9c4d326c6f6bea18e0de462ba6ef28c21d0e50c8c655ca0462ed57
+size 3852460503

model-00031-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92022dc5c0cc241dc630949e8738362c5285bc38966930607961a668c3240d90
+size 3852460417

model-00032-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9565aec68950dd5c515e164f9fd064cdf5821656590601687620392fc6fa18f
+size 3623879446

model-00033-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7972866ca47f99a166b5fb8054baa9681465bbaf1bf5c89d8bfadb980b5afb
+size 4255113745

model-00034-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb2dc2117456185e0c978aa75e36d99d5434273aa062fa7c52489ae0e095b3f
+size 3852460455

model-00035-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e002b9f2ffef52862387d06049c310a7bb2b6deb59c5bb52ec46b37749cd235e
+size 5335155738

model-00036-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7df9426982c6cb18512e7776191847c654ec9f05ad358afa89ef95ecd904ee7
+size 3953123979

model-00037-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d8e1a583ad410042085fd7268c0cd322d14ca23cf1f83c4cdf9e08c60d0564
+size 3852460559

model-00038-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a25e669f6ad3034e78f1cca3dca26bd0b2141d0bc6ee833eac2dd5e944b4a4
+size 3852460483

model-00039-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43bee111889089e1e8140652ac1d15c40a8f5c6b207e4235c356bab12c393e5
+size 3623879448

model-00040-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cf86e3f5cf5ef791978da52952a19d92e6b913745e78435d391af2fe95b0e9
+size 4255113745

model-00041-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0278469ac7a6f7e855bafeba7e1087cb3d6a93754cdaf497f943a24e9ddd5d
+size 3852460467

model-00104-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84031b9aa13aad7de1e911c7a72d1b898ddf8b17ef4870fc06a731e4f06dd61a
+size 3852460429

model-00105-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ae970622bff5612ed396c3eac2b41f3db7caff62274721896aeb264bc31314
+size 5335155736

model-00106-of-00106.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e67a0aae2f302660021f245ef8631f085ce7e191407db48ff85a65c7b7bb663
+size 1155013717

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"
+}