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
+base_model: zai-org/GLM-4.5
+tags:
+- mlx
+---
+
+This model [finding1/GLM-4.5-MLX-8.5bpw](https://huggingface.co/finding1/GLM-4.5-MLX-8.5bpw) was
+converted to MLX format from [baidu/ERNIE-4.5-300B-A47B-PT](https://huggingface.co/zai-org/GLM-4.5)
+using mlx-lm version **0.26.3** with
+`mlx_lm.convert --quantize --q-bits 8 --mlx-path MLX-8.5bpw --hf-path zai-org/GLM-4.5`.

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 +1,51 @@
+{
+    "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": 131072,
+    "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
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "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 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.54.0"
+}

model-00001-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7dfe2d1c2cabb4c9529c04bbaf7c138f7a49dd936bccc0eaa1e6958fa13d48
+size 4679461143

model-00002-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae22b403e7df1f63adfde1eb0c6620720d9153e3fa7aecfcd5f7097e3a2f7ce
+size 4182398682

model-00003-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600b7cf36271670300a3ba7f8c79be77ff9020db90cbf9b72b6ec39d424b8ce2
+size 4182398676

model-00004-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfac14663f03939a590abff41a51c8423e7f6746f7c831c4795ca4ef43e83486
+size 4182398694

model-00005-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b94dc5286afe6dc84c1d45b1d85885bf291f55decc62c4167366c2972b13a89
+size 4182398684

model-00006-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305e38eeb57fb77b8afe3174759362af895a35692fd3a6f4f803577880c87951
+size 4182398686

model-00007-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef1af69237f2724b69f57b8617e61ccbe10a4568e925962f1b2a32a657a965b
+size 4182398666

model-00008-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5926f005bcdf924d0aeb113e414e054116c6d81448afcf176a7c493c236b41
+size 4182398717

model-00009-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4275573e4099de4fbcf838be50e4075f07e9d024bbc039d015d89b616f4c9c93
+size 4182398733

model-00010-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a71287f301b80d52472e81d665a63c5dfccbc5af869dfc5a393f302c7bd99b
+size 4182398683

model-00011-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05284e55f6853704103ebbb550794b57a9963dae2209b990d88f9e69a8a50b67
+size 4182398699

model-00012-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87612b586ce531686fafe94de45fa436c4e2b3cc2f91ff94d7f6d4569c95c5f
+size 4182398709

model-00013-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e0db1d77f022bc3769dbd5023f4cf867059a66b2a0381a85cb7e16d8f32bcd
+size 4182398697

model-00014-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8025b87602b50a0059ca010eaca9cb48d5c1f10a088fbd07009d92a6a5f81cb6
+size 4182398713

model-00015-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e992f1675c709dccfa99d6934c6adf33dacf819e4e1c064914f3b2545c46d5d7
+size 4182398723

model-00016-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d17753eafc782d131960dfa8cf64a247777cfe73774bbf5ad04a6db95c8abf
+size 4182398697

model-00017-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dcd8f8fcea707360668fe837b8f0e6a9eafc6be34cbb477289a3e552e0fc76
+size 4182398729

model-00018-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7453c8883dc63466a3465a41459174be7894520fab4725646bc8465de282858
+size 4182398689

model-00019-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b37c402530593db0518ea4f49e39f63bdcf0f350c644fd41bc0bc0e3e1d766
+size 4182398729

model-00020-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bcc0ff768ffff58387a2df3e1e757bc436e56548b464366f8c901654e37343
+size 4182398729

model-00021-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c2b2777edcbac762f59ad8a5c76a6e0d3ef6ca90db8d3a03f822b6e8ca5705
+size 4182398729

model-00022-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf3c97f8d181c2367b38cea0d2fb804397240516c64814298504a69913394b3
+size 4182398681

model-00023-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf482ad4f1cffe36a3c1c5eb40171f2add65ecd94b34ef817b79ccceac99c0b
+size 4182398729

model-00024-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee66c0e50a2480169872eb311c6a619373e5a7dc3a8f8440293d2836d133839
+size 4182398711

model-00025-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a0856eeccafbbb88b868bdabcac357ccb163084a80f0ebc97c81406f0dbd75
+size 4182398729

model-00026-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60755086d5179f8b18453cd6be3cf934cbb93797b29f27fe26da626d2506f5db
+size 4182398729

model-00027-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fde50629126ef1ad8f1db7eadb35da752ddfe1aa7fef56e71c2c57aec2fdd3
+size 4182398729

model-00028-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64df858ba71227412438dac2d2ba09f61e40c5151313eb39149e3abaf5ddfcf
+size 4182398693

model-00029-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c671797d4e393f9d7486d60f3ca71aaa7dee3da318f1c2c9c6bd300fb6f64d70
+size 4182398723

model-00030-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c6e2c2a22299407f6ef1d6b2e69e4728523c6e0e2e0c5683aed82f69474947
+size 4182398729

model-00031-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b189c20cb9bd4317d830e3395255b69b13c3822a35cd70b550819203b28fef9
+size 4182398721

model-00032-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbab756a5208f9e1820ef5a5b101e28f960d641a0397235b336a42b2d984c68
+size 4182398721

model-00033-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc3987b6fd3514b71f4bc9ca331977184c5b660410cea73a0117461c7349cfe
+size 4182398729

model-00034-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a250a4a4ad9cf45f149684686ff50fe6284dd0fecfcb70deeb228a7b784b47
+size 4182398705

model-00035-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8632c562a5896d8d2c32585ae4922c250e0bb0cbf409d9becec5fe030fab16
+size 4182398725

model-00036-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b554cd614b7c146013fba9a6d16e2c95dcdd44e0c5e3f07cbf1ceb5c9a77ba2d
+size 4182398725

model-00037-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35604602bd733599a1dca2500c579c644b7d6b4519a76a4b5f6636a26c0ad1c
+size 4182398669

model-00038-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b0571aa10bc0383c76070c429c7cb5b7992d255c3cccdf7b350a6e27660d7d
+size 4182398729

model-00039-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e43024abdf5c47512a68f1a404e52f7b91cfa44a9d3aed2023943fbe8895e3
+size 4182398729

model-00040-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bbe168a4853fcc47c824c117baed08c1013865a8edc6f5e91f8e66ca01d88a9
+size 4182398729

model-00041-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc1536aa98be73261144c0a7fd1570d31fba7c53264809b62450e3f9fd164a7
+size 4182398697

model-00042-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44933f1903ce9fdef239e860fe21054292622ecf43400531cdf8905443151894
+size 4182398729

model-00043-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab71d0b1277439188c8a5d6c1b94a6c3344e6e56cae8a66c7bd20534626dc82
+size 4182398707

model-00044-of-00090.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb9ae2835839f795d9c30c723157e21d791aac3a4a84d7db03c5b07314ccce5
+size 4182398733