Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,16 @@
+---
+language:
+- en
+- zh
+library_name: mlx
+license: mit
+pipeline_tag: text-generation
+tags:
+- mlx
+base_model: zai-org/GLM-4.6
+---
+
+This model [finding1/GLM-4.6-MLX-8.5bpw](https://huggingface.co/finding1/GLM-4.6-MLX-8.5bpw) was
+converted to MLX format from [zai-org/GLM-4.6](https://huggingface.co/zai-org/GLM-4.6)
+using mlx-lm version **0.28.0** [plus pull request #494](https://github.com/ml-explore/mlx-lm/pull/494) with
+`mlx_lm.convert --quantize --q-bits 8 --hf-path zai-org/GLM-4.6 --mlx-path GLM-4.6-MLX-8.5bpw`.

chat_template.jinja

@@ -0,0 +1,103 @@
+[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) }}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- 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 loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<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 %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</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|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
+{%- endif -%}

config.json

@@ -0,0 +1,53 @@
+{
+    "architectures": [
+        "Glm4MoeForCausalLM"
+    ],
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "eos_token_id": [
+        151329,
+        151336,
+        151338
+    ],
+    "first_k_dense_replace": 3,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 202752,
+    "model_type": "glm4_moe",
+    "moe_intermediate_size": 1536,
+    "n_group": 1,
+    "n_routed_experts": 160,
+    "n_shared_experts": 1,
+    "norm_topk_prob": true,
+    "num_attention_heads": 96,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 92,
+    "num_key_value_heads": 8,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "routed_scaling_factor": 2.5,
+    "tie_word_embeddings": false,
+    "topk_group": 1,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.54.0",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "temperature": 1.0,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c44ef5e5ebf1d89b774f03e11e04e455ca7889311ccaad9efd492e1bfc854d1
+size 4679461143

model-00002-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6cb0a2982b63a781858ddfa35f2ab396be974e0e0c87fbb382a5b5f2c263d1
+size 4182398682

model-00003-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a734329db7aa1d17ce900535e7abcf414a8d48d90aea38eadae1f4c5a741b58c
+size 4182398676

model-00004-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fea95d9fd3a8bad25749c6ca6752cdd2d9ea0b71f32b06e8acc9cb801bdc11a
+size 4182398694

model-00005-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18aaba7384c5949dee4277f500610fb36468b4ad6f76503505e8c2d51b95a97
+size 4182398684

model-00006-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf84db00441f0896866f7e10f77d35373c3cc83e89c6ee658b1302169a88668
+size 4182398686

model-00007-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5905d2e46e27246958570bd82d222f939d5e12327248561a391bc82f09a0bb66
+size 4182398666

model-00008-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f22c2de236d0080e64cb346fc6dfc26f5e25d78eb3346198eeca80024bade3f
+size 4182398717

model-00009-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731bd44f94fb0b74193a78a8c45ceb68646b695d627e761570c2a8ef7fcefec3
+size 4182398733

model-00010-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543bc8ce253752236300d0d9288824b647bd5ece5bc8aac22dffcc183007fc04
+size 4182398683

model-00011-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c2a584e642c77eed23ea9f8dd1eb16f714eecad35001f0aded67e56507d151
+size 4182398699

model-00012-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600c8eaef2ce98d1b55abb8fed1d026bf863236b7d445c405284e1be0da723a2
+size 4182398709

model-00013-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b64cb7586c38935436113ef565bb76f401ccd29280c7b406357472522a2d96d
+size 4182398697

model-00014-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61bf9ba098c2a2ef09035fafe36e7a078c063c0c5db6cd97212ab8626f3696f8
+size 4182398713

model-00015-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f2131c2245de03459c58e462cfed2324411e72a91ff129b7631856ef85f558
+size 4182398723

model-00016-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11b4f9a74e7197e43c8005f58c8ac8a2c1c1f8e971d75e9f4d0812d4801a6d8
+size 4182398697

model-00017-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8094acf99d28241f204c11571cd55439b346569796005c7718279ae8bc4defdc
+size 4182398729

model-00018-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1c7d69d1508897e48a0b85a2510c7e47184c273c85774fee7fe84d2216537d
+size 4182398689

model-00019-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c9f0fed849590e4b385873282c49da718767a49e5fa7a662100b406ada6b9a
+size 4182398729

model-00020-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbebf5e9011ccbcff9aea192c83889626e57f274d26424736b934442e2b6b69
+size 4182398729

model-00021-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa6fea69d6e521c9c23ef89f822914e8e297c7cff4400554aa69c722a9a3148
+size 4182398729

model-00022-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de080298cad4c342b69f0e888fc327574099380b62196104c93f37245986024f
+size 4182398681

model-00023-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78e257a5a8101451e766ec4025842b9618469708f136466b7982b156e36c2dc
+size 4182398729

model-00024-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2625048ca1013b350f2a2db7d6ddb3ce9662821c8028545b0d26ea714fcbf0
+size 4182398711

model-00025-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3700d4c753cb2a830bfb1757b647d4467063ddea8103cd967c8732308e4d96ca
+size 4182398729

model-00026-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f4637d0c214404896939850335f8f87c71966c368255f9b8dc21b00b934330
+size 4182398729

model-00027-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e7be5050859003c5e4159fac12994ff0c72c769f9c87e3542ade38936eb8ab
+size 4182398729

model-00028-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29aa8fd6cb8c7d51af8a610b3fbacda58e7b0fbf52b65becd29610b64881d21
+size 4182398693

model-00029-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac2961ffd51d8216172a95148ad412e3932bb82956dcb07773decca6e5c8e40
+size 4182398723

model-00030-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd97d3d94982084be63c652ec558be7261d10d2b1216b424015f11c159e04571
+size 4182398729

model-00031-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd187409a7322609b71c061e577a06d754abf3ebbcd5371604cb9199739a487d
+size 4182398721

model-00032-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd9ac120a1dfc9ff8ec6bfcb4d016d958878086b0b712ede9ea8cbfab508ab3
+size 4182398721

model-00033-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ec715960a29ddef4c0e2f2545d333407deb4e0f430b802ac023f4622d088ce
+size 4182398729

model-00034-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae321de09c080a89699700220f1eb0b9cb9e746015079a063657d1fe5eb8be0
+size 4182398705

model-00035-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac08023eb426d4e8a0c4b6e89ef9b10f92d9a79076732fa0d0b117822b804b9
+size 4182398725

model-00036-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fc3c91ce64463ebe8fd285d18cb8edf39d9240fdf3ad1a8627b4ebf38790de
+size 4182398725

model-00037-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48ca8bc2b3228a093b64881a96334fc0b204591f70b043d1f1066b4a62f8807
+size 4182398669

model-00038-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84970276a03f1315268344fafa5685d9511d1d1c0f313f31a0fc2b1f6b230359
+size 4182398729

model-00039-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b86648895e01959db83ea1f6b8a8d0f9f88c5a347f2bb3ab23cceef03a210aa
+size 4182398729

model-00040-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b5414c21a628ad7106a4496d303b2b5fd0838ee11abb449945000a5862acde
+size 4182398729

model-00041-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55b43da6ae0c9686b9b02125168d8f17c2d69f1f2272693cb5442c323d5269f
+size 4182398697

model-00042-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c65ada651077626600ded5c9d2cc8176afde4f80f6c186fe5bb83946a3936b
+size 4182398729

model-00043-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f62e27a343dead8d0c0e6a3e2c26bf4f996f992d6966d140beb23e944f80a7
+size 4182398707

model-00044-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77347bd4e6668e81fafc8bcb378ed4fd1404a11fc3c2a202dd2a2a2e33a1de06
+size 4182398733

model-00045-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08f81cde434b19db4ceb3bda2bea45999a7ef0109ac0dbf94774c1f466a7110
+size 4182398705